Model comparison
GPT-5 Mini vs MiniMax-M2.1
GPT-5 Mini is the stronger model overall, scoring 41.8 to 38.9 on the Noometry Index.
Last verified . 20 shared benchmarks.
MiniMaxSummary
- They share 20 benchmarks with published results for both. GPT-5 Mini scores higher in 5 categories and MiniMax-M2.1 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 38.3.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- GPT-5 Mini accepts more context: 400K tokens versus 205K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | MiniMax-M2.1 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 41.8 | 38.9 |
| Released | 2025-08-07 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | 400K | 205K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.25 | $0.30 |
| Output $ / M tokens | $2 | $1.20 |
| Results tracked | 60 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Mini: 40.1 (#146), MiniMax-M2.1: 40.4 (#143)
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1406 | 1421 |
| ALE-Bench | 799.77 | 623.83 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| LMArena WebDev | — | 1384 |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| WeirdML | 52.7% | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use GPT-5 Mini leads
GPT-5 Mini: 31.1 (#70), MiniMax-M2.1: 27.9 (#98)
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | 34.8% | 36.6% |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 23.9 (#168), MiniMax-M2.1: 16.6 (#302)
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1380 | 1411 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 11.2% |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| Epoch Capabilities Index | 145.52 | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), MiniMax-M2.1: 38.3 (#138)
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1378 | 1397 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), MiniMax-M2.1: 38.3 (#147)
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | 12.9% | 11.8% |
| LMArena Expert | 1379 | 1431 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), MiniMax-M2.1: —
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual MiniMax-M2.1 leads
GPT-5 Mini: 48.9 (#137), MiniMax-M2.1: 50.0 (#128)
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1363 | 1378 |
| LMArena Chinese | 1385 | 1430 |
| LMArena French | 1386 | 1404 |
| LMArena German | 1366 | 1381 |
| LMArena Japanese | 1341 | 1287 |
| LMArena Korean | 1308 | 1298 |
| LMArena Russian | 1362 | 1387 |
| LMArena Spanish | 1355 | 1397 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), MiniMax-M2.1: 73.8 (#112)
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1400 |
| IFEval | 92.7% | — |
Long Context MiniMax-M2.1 leads
GPT-5 Mini: 41.9 (#132), MiniMax-M2.1: 43.2 (#101)
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1355 | 1416 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference MiniMax-M2.1 leads
GPT-5 Mini: 55.2 (#148), MiniMax-M2.1: 58.3 (#120)
| Benchmark | GPT-5 Mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1373 | 1392 |
| LMArena Creative Writing | 1325 | 1361 |
| LMArena Multi-Turn | 1363 | 1396 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than MiniMax-M2.1?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 38.9 on the Noometry Index.
Which is cheaper, GPT-5 Mini or MiniMax-M2.1?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is GPT-5 Mini or MiniMax-M2.1 better for coding?
They score almost the same on coding (40.1 vs 40.4); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 205K.
How many benchmarks do GPT-5 Mini and MiniMax-M2.1 share?
20 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and MiniMax-M2.1 has 22.