Models / Mistral Medium 3.5

Mistral AI

Mistral Medium 3.5

Mistral Medium 3.5 is strongest at speed under pressure; most buyers will do better with one of the alternatives below. The cheapest model of similar intelligence is Granite 4.2 8B, at $0.08 per million tokens against $3.00.

Results 16 Nov 2026 · 133 results · 8 sources

Test Mistral Medium 3.5 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$1.50 in · $7.50 out
Mistral AI's list price, 10 Nov 2026 · compare prices$0.15 cached input · 50% off in batch
Speed
157 tokens a second; on its test prompt the answer starts after 13.3 s, thinking time included
Artificial Analysis, on its usual API
Intelligence Index
14.2
Artificial Analysis
Spring Prompt overall
34th of 36 score 15 of 100 · how it works
Spring Prompt Score
23 of 100 30th of 32 · 5 of 5 benchmarks · our own tests only
Developer
Mistral AI, based in France
Weights not published
Released
28 Apr 2026
262,144 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 115th of 185Claude Opus 5.5 33rd of 35Claude Fable 5.2 $3.00 blended, 73rd percentilecheapest: Mistral Nemo 19th of 65Nemotron 3.5 Super VL
Models priced $3–10 per million tokens 32nd of 38Claude Opus 5.5 15th of 15Claude Opus 5.5 sets this group 1st of 15leads
Models with similar intelligence sets this group – $3.00 blended, 94th percentilecheapest: Granite 4.2 8B 4th of 10gpt-oss-120b
Models writing 100–200 tokens a second 17th of 21Claude Sonnet 5.5 7th of 7Muse Wonder $3.00 blended, 65th percentilecheapest: Qwen3.5-9B sets this group
Models from developers based in the EUall Mistral AI's 2nd of 15Mistral Large 4 – $3.00 blended, 87th percentilecheapest: Mistral Nemo 3rd of 6Ministral 3 3B

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

Measured cost per task

API cost recorded in our benchmark runs, excluding judging.

TaskBenchmarkCost per task
Product listingCatalogBench≈ $0.008
DeckDeckBench≈ $0.045
Survey plan and analysisSurveyBench≈ $0.073
Game of blitz chessBulletBench≈ $0.026

Cheapest model that passes

On our benchmarks that define a pass for each task: what one passing answer cost in our run, failed attempts included, and whether a cheaper model passed.

  • CatalogBench · cost per 1,000 accepted listings
    Mistral Medium 3.5: $26.90 (50 of 168 attempts), 14 of 25. Cheapest: GPT-6 Luna at $0.70 (114 of 168 attempts). It passed at least as often.
  • DeckBench · cost per presentable deck
    Mistral Medium 3.5: no presentable decks (0 of 6 tasks). Cheapest: GPT-6.1 Terra at $0.13 (3 of 6 tasks).
  • SurveyBench · cost per sound survey task
    Mistral Medium 3.5: no sound survey tasks (0 of 9 tasks). Cheapest: GPT-6 Luna at $0.03 (3 of 9 tasks).

Cost per attempt divided by the share that passed, at the run date's prices, excluding judging. Each model at its cheapest setting per passing answer. With a handful of tasks, a pass or two either way is within chance. No estimate where a run had missing outputs, because their cost may not have been recorded.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $3–10 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live 23rd of 32 available · 13th of 14 at its price
BenchmarkMistral Medium 3.5Rank among availableBest available
CatalogBenchCatalogBench: reliably publish-ready 17.9% 26th of 32 GPT-6 Astra 75.0%
CatalogBenchCatalogBench (sales brief): reliably publish-ready 10.7% 17th of 32 GPT-6 Astra 69.6%
Decks from an analysisTurning a finished analysis into a deck you could present as it is 31st of 32 available · 15th of 15 at its price
BenchmarkMistral Medium 3.5Rank among availableBest available
DeckBenchDeckBench: deck rating 598 31st of 32 Qwen4-Max 1,585
User surveysPlanning a user survey and reading its results without being misled 21st of 23 available · 10th of 10 at its price
BenchmarkMistral Medium 3.5Rank among availableBest available
SurveyBenchSurveyBench: analysis rating 587 21st of 23 Claude Fable 5.2 1,641
Marketing planningPlanning a year of ad spend without overspending 32nd of 32 available · 14th of 14 at its price
BenchmarkMistral Medium 3.5Rank among availableBest available
ROASBenchROASBench: overall score 15.2 32nd of 32 Claude Fable 5.2 61.3
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 100th of 159 available · 33rd of 35 at its price
BenchmarkMistral Medium 3.5Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 50.6% 59th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 15.1% 56th of 104 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 123rd of 187 available · 33rd of 39 at its price
BenchmarkMistral Medium 3.5Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 14.2 115th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 13.8% 118th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 74.8% 109th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 85th of 169 available · 28th of 34 at its price
BenchmarkMistral Medium 3.5Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,427 74th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 45.5 64th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 98th of 139 available · 29th of 31 at its price
BenchmarkMistral Medium 3.5Rank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,431 75th of 109 Gemini 4 Argon 1,511
  • Vectara Hallucination Leaderboard: has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) 10th of 35 available · 5th of 14 at its price
BenchmarkMistral Medium 3.5Rank among availableBest available
BulletBenchBulletBench Lightning 10+1: ladder Elo 529 10th of 18 Gemini 3.5 Flash-Lite 892
BulletBenchBulletBench Bullet 60s: ladder Elo 572 8th of 33 Gemini 3.8 Flash 1,068

Nearest alternatives

Against Mistral Medium 3.5 at $3.00 blended, Intelligence Index 14.2. "Similar intelligence" means within 4 points or better.

Where to run it

2 hosts on OpenRouter at the standard service tier, with a median of $3.15 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Mistralnot stated$1.50$7.50$3.00
Mistralnot stated$1.65$8.25$3.30

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Mistral Medium 3.5Claude Opus 5.5
most intelligent at $3–10 per million tokens
Granite 4.2 8B
cheapest with similar intelligence
gpt-oss-120b
fastest with similar intelligence
Mistral Large 4
most intelligent from the EU
Price per million tokens $3.00 $8.00$0.08$0.20$2.06
Tokens a second 157 966525960
Intelligence Index 14.2 57.611.111.638.4
Spring Prompt overall 15 82––25
Rank among available models, by use case
Product listings 23rd of 32 13th––27th
Decks from an analysis 31st of 32 7th––30th
User surveys 21st of 23 4th––17th
Marketing planning 32nd of 32 9th––23rd
Agents and tool use 100th of 159 3rd126th125th37th
Professional work – 3rd–49th–
Reasoning and knowledge 123rd of 187 1st138th118th54th
Writing 85th of 169 5th158th124th–
Sticking to the facts 98th of 139 3rd137th129th–
Speed under pressure 10th of 35 –––25th

Shaded figures are better than Mistral Medium 3.5's. A dash means no result.

Research and examples

Where it has been measured

Fastest of the 15 models priced $3–10 per million tokens, and 2nd most intelligent of the 15 models from developers based in the EU (all Mistral AI's). 32nd most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, in the bottom quarter for decks from an analysis, user surveys and marketing planning.

Every result

133 published results from 8 sources, each in the source's own units, with the configuration that produced it.

BulletBench · measured by Spring Prompt · 25 results
MeasureValueRankConfigurationDated
BulletBench Blitz 3+2: cost per gameUS dollars, lower is better $0.0261 5 of 22 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
BulletBench Blitz 3+2: games lost on time% of games, lower is better 0.0% 1 of 22 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
BulletBench Blitz 3+2: invalid moves% of moves, lower is better 0.4% 19 of 22 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
BulletBench Blitz 3+2: ladder Eloladder Elo, higher is better 555
396–765
17 of 22 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
BulletBench Blitz 3+2: median move timemilliseconds, lower is better 0.5 s 1 of 22 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
BulletBench Bullet 60s: cost per gameUS dollars, lower is better $0.0420 60 of 71 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Bullet 60s: cost per gameUS dollars, lower is better $0.0354 59 of 71 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: games lost on time% of games, lower is better 8.3% 28 of 71 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Bullet 60s: games lost on time% of games, lower is better 0.0% 1 of 71 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: invalid moves% of moves, lower is better 0.8% 69 of 71 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Bullet 60s: invalid moves% of moves, lower is better 0.4% 66 of 71 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: ladder Eloladder Elo, higher is better 385
276–464
45 of 71 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Bullet 60s: ladder Eloladder Elo, higher is better 572
428–708
12 of 71 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: median move timemilliseconds, lower is better 0.5 s 9 of 71 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Bullet 60s: median move timemilliseconds, lower is better 0.5 s 7 of 71 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: cost per gameUS dollars, lower is better $0.0297 45 of 48 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Lightning 10+1: cost per gameUS dollars, lower is better $0.0491 46 of 48 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: games lost on time% of games, lower is better 0.0% 1 of 48 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Lightning 10+1: games lost on time% of games, lower is better 0.0% 1 of 48 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: invalid moves% of moves, lower is better 0.3% 41 of 48 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Lightning 10+1: invalid moves% of moves, lower is better 0.0% 1 of 48 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: ladder Eloladder Elo, higher is better 529
308–680
24 of 48 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Lightning 10+1: ladder Eloladder Elo, higher is better 529
361–669
24 of 48 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: median move timemilliseconds, lower is better 0.5 s 6 of 48 Mistral Medium 3.5
provider default reasoning
1 Oct 2026
BulletBench Lightning 10+1: median move timemilliseconds, lower is better 0.5 s 9 of 48 Mistral Medium 3.5 (no reasoning)
none reasoning
1 Oct 2026

Not shown: Not your cost: prices are those charged on the run date.

CatalogBench · measured by Spring Prompt · 31 results
MeasureValueRankConfigurationDated
CatalogBench (sales brief): channel rules broken% of products, lower is better 1.2% 25 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): claims to check% of products, lower is better 25.6% 29 of 32 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): content quality% of checks, higher is better 94.1% 31 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): failed outputs% of products, lower is better 0.0% 1 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): missing UK information% of products, lower is better 0.0% 1 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): not findable% of products, lower is better 10.1% 31 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): publish-ready listings% of products, higher is better 17.3% 22 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): reliably publish-ready% of products, higher is better 10.7% 17 of 34 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): unsupported claims% of products, lower is better 76.8% 25 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): unsupported claimsclaims per product, lower is better 3.55 27 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): wrong attributes% of products, lower is better 36.3% 33 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench (sales brief): wrong category or variant% of products, lower is better 13.1% 35 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: channel compliance% of products, higher is better 100.0% 1 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: channel rules broken% of products, lower is better 0.0% 1 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: claims to check% of products, lower is better 3.6% 29 of 32 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: conflicts caught% of conflicts, higher is better 90.9% 34 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: content quality% of checks, higher is better 94.1% 33 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: cost per productUS dollars, lower is better $0.0080 16 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: decision accuracy% of decisions, higher is better 92.6% 32 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: failed outputs% of products, lower is better 0.0% 1 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: field accuracy% of missing fields, higher is better 91.7% 30 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: invented values% of filled values, lower is better 0.0% 1 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: missing UK information% of products, lower is better 0.0% 1 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: not findable% of products, lower is better 14.3% 34 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: publish-ready listings% of products, higher is better 29.8% 29 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: reliably publish-ready% of products, higher is better 17.9% 26 of 34 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: time per productseconds, lower is better 4.90 2 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: unsupported claims% of products, lower is better 49.4% 32 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: unsupported claimsclaims per product, lower is better 1.74 32 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: wrong attributes% of products, lower is better 31.0% 32 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026
CatalogBench: wrong category or variant% of products, lower is better 11.3% 35 of 35 Mistral Medium 3.5
provider default reasoning
30 Sep 2026

Not shown: Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.

DeckBench · measured by Spring Prompt · 17 results
MeasureValueRankConfigurationDated
DeckBench: accurate decks% of tasks, higher is better 0.0% 29 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: caveat dropped% of tasks, lower is better 0.0% 1 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: clean layout% of tasks, higher is better 66.7% 8 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: cost per deckUS dollars, lower is better $0.0448 12 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: deck ratingrating, higher is better 598
501–674
33 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: design quality% of the maximum, higher is better 43.7% 31 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: draft figure quoted% of tasks, lower is better 50.0% 27 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: findings missing% of tasks, lower is better 0.0% 1 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: head-to-head win rate% of comparisons, higher is better 25.2% 32 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: layout defects% of tasks, lower is better 33.3% 8 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: misleading metric used% of tasks, lower is better 0.0% 1 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: presentable decks% of tasks, higher is better 0.0% 15 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: recommendation late or wrong% of tasks, lower is better 50.0% 26 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: slides needing work% of tasks, lower is better 50.0% 17 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: time per deckseconds, lower is better 25.0 2 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: unsupported claims% of tasks, lower is better 33.3% 24 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026
DeckBench: unsupported numbers% of tasks, lower is better 0.0% 1 of 34 Mistral Medium 3.5
provider default reasoning
6 Oct 2026

Not shown: Not your analysis or your brand: invented companies, six public tasks, one deck per model per task at the provider's default reasoning setting.

ROASBench · measured by Spring Prompt · 9 results
MeasureValueRankConfigurationDated
ROASBench: audience scorescore out of 100, higher is better 28.5 35 of 35 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
ROASBench: business scorescore out of 100, higher is better 3.4 35 of 35 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
ROASBench: consistency scorescore out of 100, higher is better 8.7 34 of 35 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
ROASBench: contribution profitsimulated US dollars, higher is better −$159,882 34 of 35 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
ROASBench: cost of a runUS dollars, lower is better $0.15 14 of 35 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
ROASBench: months over budgetmonths of 12, lower is better 3 34 of 35 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
ROASBench: overall scorescore out of 100, higher is better 15.2 35 of 35 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
ROASBench: planning scorescore out of 100, higher is better 55.2 2 of 35 Mistral Medium 3.5
provider default reasoning
29 Sep 2026
ROASBench: return on ad spendprofit per $1 spent, higher is better −$0.17 34 of 35 Mistral Medium 3.5
provider default reasoning
29 Sep 2026

Not shown: Not real ad performance: the market is a deterministic simulation of one invented skincare brand.

SurveyBench · measured by Spring Prompt · 20 results
MeasureValueRankConfigurationDated
SurveyBench: analysis ratingrating, higher is better 587
497–652
22 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: analysis scorepoints of 100, higher is better 56.7 19 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: cost per taskUS dollars, lower is better $0.0730 12 of 24 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: head-to-head win rate% of comparisons, higher is better 26.1% 22 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: leading or double-barrelled questions% of tasks, lower is better 55.6% 18 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: mistaken next steps% of tasks, lower is better 77.8% 22 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: numbers right% of answers, higher is better 75.5% 22 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: objectives unanswerable% of tasks, lower is better 11.1% 15 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: precision ignored% of tasks, lower is better 100.0% 23 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: research scorepoints of 100, higher is better 64.2 19 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: sound research% of tasks, higher is better 0.0% 15 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: stakeholder's view presumed% of tasks, lower is better 33.3% 22 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: survey plan scorepoints of 100, higher is better 81.5 21 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: survey structure% of tasks, lower is better 11.1% 3 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: time per taskseconds, lower is better 47.5 2 of 24 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: traps handled% of traps, higher is better 59.4% 24 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: traps missed% of tasks, lower is better 100.0% 22 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: unsupported findings% of tasks, lower is better 100.0% 22 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: wrong numbers% of tasks, lower is better 100.0% 22 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026
SurveyBench: wrong recommendation% of tasks, lower is better 44.4% 17 of 25 Mistral Medium 3.5
provider default reasoning
8 Oct 2026

Not shown: Not your customers or your data: invented organisations with simulated respondents, nine public tasks, one run per model per task at the provider's default reasoning setting.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 11 results
MeasureValueRankConfigurationDated
Arena Agent: confirmed task successIPS effect estimate, higher is better -0.15
-0.18–-0.11
47 of 50 Mistral Medium 3.5 (arena agent) 2 Oct 2026
Arena Agent: praise over complaintIPS effect estimate, higher is better -0.18
-0.21–-0.14
47 of 50 Mistral Medium 3.5 (arena agent) 2 Oct 2026
Arena Agent: steerabilityIPS effect estimate, higher is better -0.06
-0.09–-0.04
41 of 50 Mistral Medium 3.5 (arena agent) 2 Oct 2026
Arena Agent: tool groundingIPS effect estimate, higher is better -0.02
-0.03–-0.01
48 of 50 Mistral Medium 3.5 (arena agent) 2 Oct 2026
Arena Text factuality: overallArena rating, higher is better 1,431
1,425–1,436
114 of 182 Mistral Medium 3.5 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,430
1,417–1,443
113 of 406 Mistral Medium 3.5 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,400
1,386–1,414
110 of 411 Mistral Medium 3.5 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,435
1,417–1,452
136 of 363 Mistral Medium 3.5 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,422
1,412–1,432
108 of 413 Mistral Medium 3.5 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,427
1,421–1,433
115 of 413 Mistral Medium 3.5 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,405
1,394–1,417
117 of 412 Mistral Medium 3.5 2 Oct 2026

Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Artificial Analysis · reported by Artificial Analysis · 14 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 46.9 104 of 187 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 14.2 262 of 413 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 74.8% 219 of 360 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 13.8% 243 of 419 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 68.8% 71 of 288 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 69.3% 206 of 407 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 157 32 of 137 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 40.2% 161 of 205 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 50.6% 108 of 188 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 33.3% 88 of 282 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 13.3 68 of 137 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 15.1% 104 of 175 Mistral Medium 3.5 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 94.2% 30 of 286 Mistral Medium 3.5 20 Oct 2026

Not shown: Not your codebase or tools.

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 60.0% 332 of 379 Mistral Medium 3.5 (high reasoning) 21 May 2026
UGI: requested-length error% off the requested word count, lower is better 18.0% 158 of 379 Mistral Medium 3.5 (no reasoning) 21 May 2026
UGI: style adherencescore from 0 to 1, higher is better 0.31 322 of 379 Mistral Medium 3.5 (high reasoning) 21 May 2026
UGI: style adherencescore from 0 to 1, higher is better 0.35 199 of 379 Mistral Medium 3.5 (no reasoning) 21 May 2026
UGI: writing scorescore out of 100, higher is better 43.9 194 of 379 Mistral Medium 3.5 (high reasoning) 21 May 2026
UGI: writing scorescore out of 100, higher is better 45.5 183 of 379 Mistral Medium 3.5 (no reasoning) 21 May 2026

Not shown: Not other format limits such as character counts or bullet counts.

Embed a score badge

A badge for its Spring Prompt Score and each of our benchmarks that ranked Mistral Medium 3.5, from the current results. Paste the code into a page or README; it links back to where the result comes from.

Mistral Medium 3.5 is #30 of 32 on the Spring Prompt Score (23 of 100, from 5 of 5 of our benchmarks), measured by Spring Prompt Spring Prompt Score · 5 of 5 benchmarks
<a href="https://springprompt.com/score#mistral-mistral-medium-3-5"><img src="https://springprompt.com/badge/score/mistral-mistral-medium-3-5.svg" alt="Mistral Medium 3.5 is #30 of 32 on the Spring Prompt Score (23 of 100, from 5 of 5 of our benchmarks), measured by Spring Prompt" height="20"></a>
Mistral Medium 3.5 is #26 of 32 on CatalogBench (Reliably publish-ready, factual brief: 17.9%), measured by Spring Prompt CatalogBench · Reliably publish-ready, factual brief
<a href="https://springprompt.com/benchmarks/catalogbench?focus=mistral-mistral-medium-3-5"><img src="https://springprompt.com/badge/catalogbench/mistral-mistral-medium-3-5.svg" alt="Mistral Medium 3.5 is #26 of 32 on CatalogBench (Reliably publish-ready, factual brief: 17.9%), measured by Spring Prompt" height="20"></a>
Mistral Medium 3.5 is #32 of 33 on DeckBench (Deck rating: 598), measured by Spring Prompt DeckBench · Deck rating
<a href="https://springprompt.com/benchmarks/deckbench?focus=mistral-mistral-medium-3-5"><img src="https://springprompt.com/badge/deckbench/mistral-mistral-medium-3-5.svg" alt="Mistral Medium 3.5 is #32 of 33 on DeckBench (Deck rating: 598), measured by Spring Prompt" height="20"></a>
Mistral Medium 3.5 is #22 of 24 on SurveyBench (Analysis rating: 587), measured by Spring Prompt SurveyBench · Analysis rating
<a href="https://springprompt.com/benchmarks/surveybench?focus=mistral-mistral-medium-3-5"><img src="https://springprompt.com/badge/surveybench/mistral-mistral-medium-3-5.svg" alt="Mistral Medium 3.5 is #22 of 24 on SurveyBench (Analysis rating: 587), measured by Spring Prompt" height="20"></a>
Mistral Medium 3.5 is #33 of 33 on ROASBench (Score: 15.2), measured by Spring Prompt ROASBench · Score
<a href="https://springprompt.com/benchmarks/roasbench?focus=mistral-mistral-medium-3-5"><img src="https://springprompt.com/badge/roasbench/mistral-mistral-medium-3-5.svg" alt="Mistral Medium 3.5 is #33 of 33 on ROASBench (Score: 15.2), measured by Spring Prompt" height="20"></a>
Mistral Medium 3.5 is #24 of 45 on BulletBench (Lightning 10+1: 529), measured by Spring Prompt BulletBench · Lightning 10+1
<a href="https://springprompt.com/benchmarks/bulletbench?focus=mistral-mistral-medium-3-5"><img src="https://springprompt.com/badge/bulletbench/mistral-mistral-medium-3-5.svg" alt="Mistral Medium 3.5 is #24 of 45 on BulletBench (Lightning 10+1: 529), measured by Spring Prompt" height="20"></a>

Will Mistral Medium 3.5 work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.