Models / MiniMax-M2.5

MiniMax

MiniMax-M2.5

MiniMax-M2.5 is strongest at reasoning and knowledge; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is DeepSeek-V4-Flash (0423), at $0.15 per million tokens against $0.52.

Superseded. MiniMax-M3 is MiniMax's newer model in this line, at $0.52 blended: see MiniMax-M3 or compare the two.

Results 16 Nov 2026 · 26 results · 6 sources

Test MiniMax-M2.5 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.29 in · $1.20 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
22.8
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
MiniMax, based in China
Weights published
Released
12 Feb 2026
200,000 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 84th of 185Claude Opus 5.5 – $0.52 blended, 38th percentilecheapest: Mistral Nemo –
Models priced $0.25–1 per million tokens 16th of 61MiMo-V2.6-Pro – sets this group –
Models with similar intelligence sets this group – $0.52 blended, 21st percentilecheapest: DeepSeek-V4-Flash (0423) –
Models from developers based in China 32nd of 75MiMo-V2.6-Pro – $0.52 blended, 46th percentilecheapest: Qwen3.5-9B –
Open-weights models 32nd of 104MiMo-V2.6-Pro – $0.52 blended, 55th percentilecheapest: Mistral Nemo –

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.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $0.25–1 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 Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 135th of 159 available · 39th of 47 at its price
BenchmarkMiniMax-M2.5Rank among availableBest available
OpenHands IndexOpenHands Index: average · reported 45.2% 21st of 31 Claude Fable 5 81.0%
Vending-Bench 2Vending-Bench 2: money after a year · reported $-23.16 52nd of 53 GPT-6 Astra $15,515
  • 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.
  • Microsoft STATE-Bench: has not measured this model.
  • Artificial Analysis: 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 91st of 187 available · 19th of 61 at its price
BenchmarkMiniMax-M2.5Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 22.8 84th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 20.5% 102nd of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 84.8% 71st of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 107th of 169 available · 34th of 58 at its price
BenchmarkMiniMax-M2.5Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,391 103rd of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 41.7 76th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 101st of 139 available · 21st of 40 at its price
BenchmarkMiniMax-M2.5Rank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 9.1% 33rd of 71 GPT-5.4 nano 3.1%
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,386 102nd of 109 Gemini 4 Argon 1,511
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against MiniMax-M2.5 at $0.52 blended, Intelligence Index 22.8. "Similar intelligence" means within 4 points or better.

Where to run it

5 hosts on OpenRouter at the standard service tier, with a median of $0.52 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.

HostQuantisationInputOutputBlended
Venicenot stated$0.27$0.95$0.44
StreamLakenot stated$0.27$1.08$0.47
AtlasCloudFP8$0.29$1.20$0.52
DigitalOceannot stated$0.30$1.20$0.52
GMICloudFP8$0.30$1.20$0.52

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.

MiniMax-M2.5MiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
DeepSeek-V4-Flash (0423)
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.52 $0.54$0.15$8.00
Tokens a second – 43–96
Intelligence Index 22.8 46.324.457.6
Spring Prompt overall – ––82
Rank among available models, by use case
Product listings – ––13th
Decks from an analysis – ––7th
User surveys – ––4th
Marketing planning – ––9th
Agents and tool use 135th of 159 23rd59th3rd
Professional work – ––3rd
Reasoning and knowledge 91st of 187 13th69th1st
Writing 107th of 169 23rd63rd5th
Sticking to the facts 101st of 139 10th81st3rd
Speed under pressure – –––

Shaded figures are better than MiniMax-M2.5's. A dash means no result.

Where it has been measured

16th most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, in the bottom quarter for agents and tool use.

Artificial Analysis lists it but has not published a speed for it yet

Every result

26 published results from 6 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
MeasureValueRankConfigurationDated
Arena Text factuality: overallArena rating, higher is better 1,386
1,382–1,389
160 of 182 MiniMax-M2.5 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,400
1,393–1,407
162 of 406 MiniMax-M2.5 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,357
1,349–1,365
170 of 411 MiniMax-M2.5 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,425
1,415–1,435
149 of 363 MiniMax-M2.5 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,381
1,375–1,387
170 of 413 MiniMax-M2.5 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,391
1,387–1,395
171 of 413 MiniMax-M2.5 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,369
1,363–1,376
169 of 412 MiniMax-M2.5 2 Oct 2026

Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Artificial Analysis · reported by Artificial Analysis · 7 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 22.8 179 of 413 MiniMax-M2.5 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 84.8% 123 of 360 MiniMax-M2.5 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 20.5% 198 of 419 MiniMax-M2.5 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 71.6% 47 of 288 MiniMax-M2.5 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 73.3% 171 of 407 MiniMax-M2.5 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 34.8% 77 of 282 MiniMax-M2.5 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 95.3% 22 of 286 MiniMax-M2.5 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 45.2% 22 of 34 MiniMax-M2.5 (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 25.0% 27 of 34 MiniMax-M2.5 (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 12.5% 25 of 34 MiniMax-M2.5 (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 47.9% 24 of 34 MiniMax-M2.5 (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 72.6% 23 of 34 MiniMax-M2.5 (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 68.1% 18 of 34 MiniMax-M2.5 (openhands) 30 Jun 2026

Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 41.0% 303 of 379 MiniMax-M2.5 12 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.38 75 of 379 MiniMax-M2.5 12 Feb 2026
UGI: writing scorescore out of 100, higher is better 41.7 209 of 379 MiniMax-M2.5 12 Feb 2026

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

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 98.2% 80 of 108 MiniMax-M2.5 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 9.1% 46 of 108 MiniMax-M2.5 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $-23.16 62 of 63 MiniMax-M2.5 1 Oct 2026

Not shown: Not a real business; one simulated market with set rules.

Will MiniMax-M2.5 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.