Compare / Mistral Medium 3.5 vs gpt-oss-120b

Mistral Medium 3.5 vs gpt-oss-120b

Which is cheaper, which is more capable, and which does better at each kind of work, from 24 results on 3 sources that measured both models.

Mistral AIMistral Medium 3.5 Released 28 Apr 2026 · $1.50 in · $7.50 out
OpenAIgpt-oss-120b Released 5 Aug 2025 · $0.10 in · $0.50 out
Mistral Medium 3.5 wins 181 too close to callgpt-oss-120b wins 5

Of the 24 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Mistral AI vs OpenAI, every model from both labs.

Mistral Medium 3.5 or gpt-oss-120b? The short answer

Pick Mistral Medium 3.5 if quality matters most: it scores higher (Intelligence Index 14.2 against 11.6). Pick gpt-oss-120b if cost matters more: it costs 15 times less per token. gpt-oss-120b is also faster.

  • gpt-oss-120b is cheaper: $0.20 against $3.00 per million tokens, 15 times less.
  • Mistral Medium 3.5 scores higher on the Artificial Analysis Intelligence Index: 14.2 against 11.6.
  • gpt-oss-120b writes faster: 259 tokens a second against 157.
  • Mistral Medium 3.5 is newer: released 28 Apr 2026, against 5 Aug 2025 for gpt-oss-120b.
  • On third-party benchmarks, on the results both models have: Mistral Medium 3.5 does better for agents and tool use, writing and sticking to the facts; gpt-oss-120b for reasoning and knowledge.

Head to head

14.2
Intelligence Index
11.6
$3.00
Price per million tokens, blendedlower is better
$0.20
157
Output speed, tokens a second
259
262,144
Context window, tokens
131,072

Every fact side by side

Mistral Medium 3.5gpt-oss-120b
Price per million tokens$1.50 in · $7.50 out$0.10 in · $0.50 out
Blended (3 in : 1 out)$3.00$0.20
Cheapest host, blended$3.00 (Mistral)$0.060 (Near AI, FP4)
Cached input, per million$0.15 cached input–
Intelligence Index14.211.6
Spring Prompt overall15–
Output speed, tokens a second157259
Context window262,144 tokens131,072 tokens
Released28 Apr 2026 (newer)5 Aug 2025
WeightsClosedOpen
Developer based inFrancethe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live 23 of 32 not measured
Decks from an analysisTurning a finished analysis into a deck you could present as it is 31 of 32 not measured
User surveysPlanning a user survey and reading its results without being misled 21 of 23 not measured
Marketing planningPlanning a year of ad spend without overspending 32 of 32 not measured
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 100 of 159 125 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 49 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 123 of 187 118 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 85 of 169 124 of 169
Sticking to the factsSummarising without inventing things, and factual answers 98 of 139 129 of 139
Speed under pressureGood decisions against a real clock (fast chess) 10 of 35 not measured

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureMistral Medium 3.5gpt-oss-120b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 99 · 187 of 387 measured 1,427 1,352
Overall · Text factualityArena rating, higher is better 97 · 142 of 163 measured 1,431 1,385
Business, management and finance · TextArena rating, higher is better 98 · 183 of 380 measured 1,430 1,352
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 139 · 162 of 249 measured 14.2 11.6high reasoning
GPQA Diamond% of questions, higher is better 140 · 119 of 232 measured 74.8% 78.2%high reasoning
Humanity's Last Exam% of questions, higher is better 139 · 118 of 250 measured 13.8% 19.6%high reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 86 · 116 of 230 measured 45.5no reasoning 38.5medium reasoning
Requested-length error · UGI% off the requested word count, lower is better 91 · 224 of 230 measured 18.0%no reasoning 107.0%medium reasoning
Style adherence · UGIscore from 0 to 1, higher is better 108 · 217 of 230 measured 0.35no reasoning 0.29medium reasoning
Show all 24 results (15 more)
MeasureMistral Medium 3.5gpt-oss-120b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 95 · 238 of 385 measured 1,400 1,278
Expert prompts · TextArena rating, higher is better 119 · 188 of 338 measured 1,435 1,357
Instruction following · TextArena rating, higher is better 92 · 204 of 387 measured 1,422 1,323
Writing, literature and language · TextArena rating, higher is better 100 · 215 of 386 measured 1,405 1,309
Artificial Analysis reported by Artificial Analysis · 11 results
Terminal-Bench 2.1% of tasks, higher is better 63 · 88 of 131 measured 50.6% 26.2%high reasoning
Terminal-Bench 4.0% of tasks, higher is better 72 · 72 of 120 measured 0.0% 0.0%high reasoning
τ-bench banking% of tasks, higher is better 60 · 67 of 121 measured 15.1% 12.8%high reasoning
Artificial Analysis Coding Indexindex score, higher is better 61 · 85 of 130 measured 46.9 30.4high reasoning
IFBench% of instructions, higher is better 59 · 58 of 195 measured 68.8% 69.0%high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 120 · 160 of 241 measured 69.3% 52.0%high reasoning
Output speedtokens per second, higher is better 22 · 8 of 78 measured 157 259high reasoning
SciCode% of problems, higher is better 85 · 101 of 121 measured 40.2% 34.0%high reasoning
Terminal-Bench Hard% of tasks, higher is better 57 · 84 of 190 measured 33.3% 23.5%high reasoning
Time to first answer tokenseconds, lower is better 52 · 45 of 78 measured 13.3 8.22high reasoning
τ²-bench telecom% of tasks, higher is better 25 · 86 of 193 measured 94.2% 65.8%high reasoning

Quick answers

Is Mistral Medium 3.5 better than gpt-oss-120b?

Pick Mistral Medium 3.5 if quality matters most: it scores higher (Intelligence Index 14.2 against 11.6). Pick gpt-oss-120b if cost matters more: it costs 15 times less per token. gpt-oss-120b is also faster.

Which is cheaper, Mistral Medium 3.5 or gpt-oss-120b?

gpt-oss-120b is cheaper: $0.20 against $3.00 per million tokens, 15 times less.

Which is faster, Mistral Medium 3.5 or gpt-oss-120b?

gpt-oss-120b writes about 259 tokens a second on its usual API, against 157 for Mistral Medium 3.5 (Artificial Analysis).

Which is better for agents and tool use, Mistral Medium 3.5 or gpt-oss-120b?

Mistral Medium 3.5 ranks 100 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 125 for gpt-oss-120b.

Which is better for reasoning and knowledge, Mistral Medium 3.5 or gpt-oss-120b?

gpt-oss-120b ranks 118 of 187 models on sale for hard questions across science, maths and general knowledge, against 123 for Mistral Medium 3.5.

Which is better for writing, Mistral Medium 3.5 or gpt-oss-120b?

Mistral Medium 3.5 ranks 85 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 124 for gpt-oss-120b.

Which is better for sticking to the facts, Mistral Medium 3.5 or gpt-oss-120b?

Mistral Medium 3.5 ranks 98 of 139 models on sale for summarising without inventing things, and factual answers, against 129 for gpt-oss-120b.

Which has the bigger context window, Mistral Medium 3.5 or gpt-oss-120b?

Mistral Medium 3.5: 262,144 tokens, against 131,072 for gpt-oss-120b.

Run Mistral Medium 3.5 and gpt-oss-120b on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.