Model comparison
GPT-5.4 Pro vs MiniMax-M3
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 43.8 on the Noometry Index. MiniMax-M3 costs 129× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
MiniMaxSummary
- They share 5 benchmarks with published results for both. GPT-5.4 Pro scores higher in 4 categories and MiniMax-M3 in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 30.1.
- The biggest single-benchmark swing is Chess Puzzles: 58.6% for GPT-5.4 Pro and 14% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 1M.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | MiniMax-M3 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 58.9 | 43.8 |
| Released | 2026-03-05 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1M |
| Max output | 128K | 512K |
| Input $ / M tokens | $30 | $0.30 |
| Output $ / M tokens | $180 | $1.20 |
| Results tracked | 16 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
GPT-5.4 Pro: 43.2 (#90), MiniMax-M3: 41.8 (#118)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1469 |
| ALE-Bench | — | 640.02 |
Agentic & Tool Use Not comparable
GPT-5.4 Pro: —, MiniMax-M3: 22.6 (#130)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), MiniMax-M3: 30.1 (#87)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| SimpleBench | 74.1% | 45.8% |
| CritPt | 30% | 3.7% |
| Chess Puzzles | 58.6% | 14% |
| Epoch Capabilities Index | 158.93 | 146.95 |
| ARC-AGI-2 | 83.3% | — |
| NYT Connections (extended) | — | 65.1% |
| ARC-AGI-1 | 94.5% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1447 |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), MiniMax-M3: 40.0 (#95)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |
| LMArena Math | — | 1429 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), MiniMax-M3: 58.4 (#35)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 94.6% | 90.9% |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1461 |
Multimodal Not comparable
GPT-5.4 Pro: —, MiniMax-M3: 40.2 (#51)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |
Multilingual Not comparable
GPT-5.4 Pro: —, MiniMax-M3: 53.0 (#75)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | — | 1420 |
| LMArena Chinese | — | 1463 |
| LMArena French | — | 1447 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1432 |
Instruction Following Not comparable
GPT-5.4 Pro: —, MiniMax-M3: 75.5 (#62)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | — | 1433 |
Long Context Not comparable
GPT-5.4 Pro: —, MiniMax-M3: 44.2 (#72)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | — | 1445 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, MiniMax-M3: 62.1 (#83)
| Benchmark | GPT-5.4 Pro | MiniMax-M3 |
|---|---|---|
| LMArena Text | — | 1433 |
| LMArena Creative Writing | — | 1404 |
| EQ-Bench 4 | — | 1150 |
| LMArena Multi-Turn | — | 1442 |
Frequently asked questions
Is GPT-5.4 Pro better than MiniMax-M3?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 43.8 on the Noometry Index. MiniMax-M3 costs 129× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 Pro or MiniMax-M3?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is GPT-5.4 Pro or MiniMax-M3 better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 1M.
How many benchmarks do GPT-5.4 Pro and MiniMax-M3 share?
5 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and MiniMax-M3 has 41.