Model comparison
GPT-5.1 vs MiniMax-M3
GPT-5.1 is the stronger model overall, scoring 49.0 to 43.8 on the Noometry Index. MiniMax-M3 costs 6.5× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
MiniMaxSummary
- They share 33 benchmarks with published results for both. GPT-5.1 scores higher in 9 categories and MiniMax-M3 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.1 leads 52.2 to 40.0.
- The biggest single-benchmark swing is Chess Puzzles: 32% for GPT-5.1 and 14% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- MiniMax-M3 accepts more context: 1M tokens versus 400K.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1 | MiniMax-M3 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 49.0 | 43.8 |
| Released | 2025-11-13 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | 400K | 1M |
| Max output | 128K | 512K |
| Input $ / M tokens | $1.25 | $0.30 |
| Output $ / M tokens | $10 | $1.20 |
| Results tracked | 63 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.4 (#66), MiniMax-M3: 41.8 (#118)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| LMArena WebDev | 1395 | 1482 |
| SciCode | 43.3% | 47.1% |
| LMArena Coding | 1454 | 1469 |
| ALE-Bench | 1,192 | 640.02 |
| SWE-bench Verified | 68% | — |
| FrontierCode | — | 14.7% |
| SWE-bench Verified (bash only) | 66% | — |
| GSO | 13.7% | — |
| WeirdML | 60.8% | — |
| LiveBench Coding | 72.5% | — |
Agentic & Tool Use GPT-5.1 leads
GPT-5.1: 32.7 (#60), MiniMax-M3: 22.6 (#130)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| Vending-Bench 2 | 1,473 | 2,158 |
| Terminal-Bench | 47.6% | — |
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| DeepResearch Bench | 42.8% | — |
| GBAEval | — | 0.9% |
| LMArena Search | 1199 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), MiniMax-M3: 30.1 (#87)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| SimpleBench | 53.2% | 45.8% |
| CritPt | 4.9% | 3.7% |
| Chess Puzzles | 32% | 14% |
| LMArena Hard Prompts | 1457 | 1447 |
| Mystery Game Puzzles | 19% | 8% |
| DTBench | 90.1% | 78.9% |
| LMCA | 43.9% | 33.7% |
| Epoch Capabilities Index | 149.64 | 146.95 |
| ForecastBench | 58.1 | 61.4 |
| ARC-AGI-2 | 17.6% | — |
| NYT Connections (extended) | — | 65.1% |
| ARC-AGI-1 | 72.8% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| LiveBench Data Analysis | 72.1% | — |
| Surface Evolver Bench | — | 55% |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), MiniMax-M3: 40.0 (#95)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 71.1% |
| LMArena Math | 1447 | 1429 |
| ProofBench | — | 18% |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge MiniMax-M3 leads
GPT-5.1: 50.6 (#71), MiniMax-M3: 58.4 (#35)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 87.6% | 90.9% |
| LMArena Expert | 1470 | 1461 |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| MMLU-Pro | 57.9% | — |
| Vectara Hallucination Rate | 10.9% | — |
| GPQA (HELM) | 44.2% | — |
Multimodal GPT-5.1 leads
GPT-5.1: 44.8 (#19), MiniMax-M3: 40.2 (#51)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1250 | 1253 |
| LMArena Document | 1403 | 1435 |
| VPCT | 58.7% | — |
Multilingual Too close to call
GPT-5.1: 53.8 (#56), MiniMax-M3: 53.0 (#75)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1431 | 1420 |
| LMArena Chinese | 1495 | 1463 |
| LMArena French | 1450 | 1447 |
| LMArena German | 1438 | 1426 |
| LMArena Japanese | 1453 | 1381 |
| LMArena Korean | 1401 | 1372 |
| LMArena Russian | 1435 | 1428 |
| LMArena Spanish | 1433 | 1432 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), MiniMax-M3: 75.5 (#62)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1443 | 1433 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), MiniMax-M3: 44.2 (#72)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1447 | 1445 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), MiniMax-M3: 62.1 (#83)
| Benchmark | GPT-5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1443 | 1433 |
| LMArena Creative Writing | 1427 | 1404 |
| LMArena Multi-Turn | 1450 | 1442 |
| WildBench | 86.3% | — |
| EQ-Bench 4 | — | 1150 |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than MiniMax-M3?
GPT-5.1 is the stronger model overall, scoring 49.0 to 43.8 on the Noometry Index. MiniMax-M3 costs 6.5× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, GPT-5.1 or MiniMax-M3?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or MiniMax-M3 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 400K.
How many benchmarks do GPT-5.1 and MiniMax-M3 share?
33 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and MiniMax-M3 has 41.