Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
MiniMax · Open Weight · rank 86 · bench-align-v5
MiniMax M3 is built for reasoning. It ranks in the top quarter for instruction following (top 4% of 159 scored models) and reasoning (top 9% of 216 scored models), by BenchLM's published scores. It accepts text, images and video and produces text.
MiniMax M3 by MiniMax scores 52.6 overall, costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, and carries a context window of 1M tokens — observed 2026-11-21.
Every published price component, including cache reads and writes.
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 99.98 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 84 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
| $0.88 |
| Batch cache read / 1M tokens (OpenRouter batch) | $0.0448 |
Batch API rate (asynchronous jobs), from OpenRouter's batch listing.
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 18.9 | #120 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 92.9 | #13 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 39.0 | #55 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | -5.5 | #92 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 44.9 | #46 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 91.4 | #29 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| GPQA Diamond (Vals) GPQA Diamond, Vals AI run | 92.7 | #14 | Graduate-level science questions | Expert reasoning | Vals AI GPQA Diamond, Vals AI run leaderboard |
| MMLU-Pro (Vals) MMLU-Pro, Vals AI run | 84.2 | #60 | Academic multiple-choice questions | Broad academic knowledge | Vals AI MMLU-Pro, Vals AI run leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 66.0 | #55 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 66.0 | #29 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| SWE-bench Verified Software Engineering Benchmark Verified | 80.5 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| USAMO 2026 United States of America Mathematical Olympiad 2026 | 85.71 | #3 | 6 proof-based problems | International olympiad level | United States of America Mathematical Olympiad |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 83.0 | #18 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 17.2 | #37 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 3.7 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-IFBench Artificial Analysis IFBench | 82.9 | #1 | Verifiable instruction constraints | Instruction precision | Artificial Analysis IFBench Benchmark Leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA Briefcase Artificial Analysis Briefcase | 1090 | #43 | Professional knowledge-work tasks | Professional work | Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 21.3 | #45 | Business-process automation tasks | Agentic automation | Artificial Analysis AutomationBench Benchmark Leaderboard |
| AA EnterpriseOps-Gym Artificial Analysis EnterpriseOps-Gym | 32.1 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 78.1 | #26 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 78.6 | #34 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| Design Arena Website Design Arena Website Elo | 1244 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chess Puzzles Chess Puzzles (Epoch AI) | 17.0 | #67 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | Chess Puzzles (Epoch AI) |
| Mystery Game Puzzles Mystery Game Puzzles (Epoch AI) | 8.0 | #69 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | Mystery Game Puzzles (Epoch AI) |
| BabaIsBench BabaIsBench (Baba Is You intro levels, pass@1) | 46 |
A second, independent score source. Epoch’s own figures in Epoch’s units, one line per model version Epoch evaluated (effort setting as Epoch labels it). They are not part of this site’s capability scores or rank.
| Benchmark | Variant | Score | Epoch date | Evidence |
|---|---|---|---|---|
| GPQA Diamond Accuracy on graduate-level science multiple-choice questions (best score across scorers). Unit: fraction (0–1); higher is better. | default | 0.9091 ± 0.0205 | 2026-08-10 | |
| none | 0.8131 ± 0.0278 | 2026-08-10 | ||
| OSWorld 2.0 Binary task success on computer-use tasks, as compiled by Epoch from the OSWorld 2.0 leaderboard. Unit: fraction (0–1); higher is better. | default standard | 0.046 | — |
Source: Epoch AI, CC BY 4.0 (licence), benchmark data read once a day.
People's votes between two anonymous answers on arena.ai, one board per task. LMArena's own ratings and ranks, one line per model version it rates; not part of this site's capability scores or rank.
| Board | Variant | Rating | Votes | Rank | Published | Evidence |
|---|---|---|---|---|---|---|
| Vision Arena People's votes between two answers about the same image, style-controlled. | — | 1,231 ± 6 | 21,034 | 74 | 2026-11-19 |
Source: LMArena, CC BY 4.0 (licence), leaderboard data read once a day.
| #19 |
| 500 verified issues |
| Professional software engineering |
| SWE-bench: Can Language Models Resolve Real-World GitHub Issues? |
| SWE-bench Pro SWE-bench Pro | 59 | #37 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| OpenHarmony Bench v1.0 OpenHarmony Bench v1.0 | 48.4 | #14 | 153 app-development and bug-fix tasks | End-to-end OpenHarmony application development | OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development |
| NL2Repo NL2Repo | 42.13 | #26 | Natural language to repository tasks | System-level software comprehension | MiniMax M2.7: Early Echoes of Self-Evolution |
| AA Coding Index Artificial Analysis Coding Index | 58.6 | #43 | Cross-benchmark coding index | Display-only external reference | Artificial Analysis model leaderboards |
| AA-SciCode Artificial Analysis SciCode | 47.1 | #68 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| VIBE V2 VIBE V2 | 50.1 | #1 | End-to-end coding-agent tasks | Frontier coding-agent workflows | MiniMax M3 model card |
| SVG-Bench SVG-Bench | 63.7 | #1 | SVG generation and editing tasks | Visual coding and structured graphics generation | MiniMax M3 model card |
| KernelBench Hard KernelBench Hard | 28.8 | #1 | Hard GPU kernel coding tasks | Specialized systems programming | MiniMax M3 model card |
| LiveCodeBench (Vals) LiveCodeBench, Vals AI run | 82.2 | #51 | Competitive programming problems (easy, medium, hard) | Frontier coding | Vals AI LiveCodeBench, Vals AI run leaderboard |
| SWE-bench (Vals) SWE-bench, Vals AI run | 75.0 | #41 | Real repository issues by human time bucket | Frontier coding agents | Vals AI SWE-bench, Vals AI run leaderboard |
| #96 |
| Research-level physics questions |
| Research-level physics reasoning |
| CritPt Benchmark Leaderboard |
| #30 |
| Enterprise operations workflows |
| Enterprise agent operations |
| Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard |
| AA Harvey LAB v1.0 Artificial Analysis Harvey LAB-AA v1.0 | 88.4 | #11 | Legal agent tasks | Professional legal work | Artificial Analysis Harvey LAB-AA Benchmark Leaderboard |
| AA Tau3 Banking Artificial Analysis Tau3-Banking | 15.3 | #29 | Banking tool-use workflows | Agentic banking workflows | Artificial Analysis Tau3-Banking Benchmark Leaderboard |
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 66 | #30 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 66.0 | #61 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| BrowseComp BrowseComp | 83.52 | #22 | Research questions requiring browsing | Hard web research | BrowseComp |
| GDPval-AA GDPval-AA | 1304 | #57 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 37.1 | #50 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Agentic Index Artificial Analysis Agentic Index | 30.8 | #28 | Cross-benchmark agentic index | Display-only external reference | Artificial Analysis model leaderboards |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 2.0 | #44 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 9.8 | #46 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| AA-AnalystAgent Artificial Analysis AnalystAgent | 10.0 | #36 | Spreadsheet and document analysis questions | Business and data analysis | AA-AnalystAgent Benchmark Leaderboard |
| OSWorld-Verified OSWorld-Verified | 70.06 | #25 | 369 real-world computer tasks (361 when eight Google Drive tasks are excluded) | Multi-step desktop and cross-application workflows | OSWorld |
| OSWorld 2.0 OSWorld 2.0 | 4.6 | #23 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks |
| MCP Atlas MCP Atlas | 74.2 | #27 | Tool-integrated agent tasks | Advanced tool use | Introducing GPT-5.4 mini and nano |
| τ²-bench results τ²-Bench Tool-Agent-User Evaluation | 88.9 | #46 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment |
| Claw-Eval Claw-Eval | 74.5 | #5 | 300 tasks, 2,159 rubrics | Real-world general, multi-turn, and native multimodal agent execution | Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents |
| ResearchClawBench ResearchClawBench | 19.8 | #5 | 40 tasks across 10 scientific domains | Scientific research re-discovery | ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research |
| GDPval rubrics GDPval rubrics | 74.7 | #2 | Economically valuable work tasks | Professional agentic workflows | MiniMax M3 model card |
| BankerToolBench BankerToolBench | 76.1 | #3 | Finance and banking tool-use tasks | Professional finance-agent workflows | MiniMax M3 model card |
| Terminal-Bench 2.1 (Vals) Terminal-Bench 2.1, Vals AI run | 53.6 | #51 | Difficult terminal tasks | Frontier agentic | Vals AI Terminal-Bench 2.1, Vals AI run leaderboard |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 0 | #29 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | MazeBench Results |
| Terminal-Bench 4.1 Terminal-Bench 4.1 | 7.60 | #43 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| AA Cyber Index Artificial Analysis Cyber Index | 22.4 | #19 | Three defensive cybersecurity evaluations | Real-world vulnerability discovery and patching | Artificial Analysis Cyber Index |
| CWE-Bench-AA Artificial Analysis CWE-Bench-AA | 41.7 | #19 | Real-world vulnerability patching tasks | Automated vulnerability remediation | CWE-Bench-AA Benchmark Leaderboard |
| DeepsecBench-AA Artificial Analysis DeepsecBench-AA | 1.1 | #22 | Vulnerability discovery in real codebases | Security code review | DeepsecBench-AA Benchmark Leaderboard |
| CyberGym-E2E-AA Artificial Analysis CyberGym-E2E-AA | 24.4 | #11 | 131 end-to-end vulnerability reproduction and patching tasks | Real-world cybersecurity | CyberGym-E2E-AA Benchmark Leaderboard |
| #48 |
| Website generation comparisons |
| Design and website generation |
| OpenRouter Grok 4.3 benchmarks |
| OfficeQA Pro OfficeQA Pro | 45.1 | #15 | Document and spreadsheet tasks | Enterprise grounded reasoning | OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning |
| OmniDocBench 1.5 OmniDocBench 1.5 | 91.6 | #2 | Document understanding tasks | Grounded document reasoning | Introducing GPT-5.4 mini and nano |
| Video-MME (with subtitle) Video-MME with subtitle | 85.4 | #10 | Video understanding | Multimodal video reasoning | Qwen3.6 launch benchmarks |
| VideoMMMU VideoMMMU | 84.6 | #8 | Video-grounded expert reasoning | Frontier multimodal video reasoning | Qwen3.6 launch benchmarks |
| #26 |
| 8 intro levels of Baba Is You, three attempts per level (Stage 0); 15 further levels run once (Stage 1) |
| Rule-rewriting puzzles that need planning over many moves |
| Baba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost? (Quesma) |
| NYT Connections NYT Connections LLM Benchmark (extended version) | 65.1 | #59 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | NYT Connections LLM Benchmark (Lech Mazur, GitHub) |
| StealthMark StealthMark Intelligence Benchmarks (overall score) | 38.6 | #33 | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon | Chained physical reasoning, planning without tools and precise visual construction | StealthMark: The AI Benchmark Explained (Stealth Models) |
| SkillsBench official leaderboard (BenchFlow) SkillsBench v1.1 official leaderboard (BenchFlow) | 53.0 | #10 | 87 tasks in 8 domains (SkillsBench v1.1) | Multi-step agent tasks | SkillsBench leaderboard |