Model comparison
GPT-5.4 Pro vs MiniMax-M2
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 37.4 on the Noometry Index. MiniMax-M2 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 . 0 shared benchmarks.
MiniMaxSummary
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 19.4.
- MiniMax-M2 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 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | MiniMax-M2 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 58.9 | 37.4 |
| Released | 2026-03-05 | 2025-10-27 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 205K |
| Max output | 128K | 131K |
| Input $ / M tokens | $30 | $0.30 |
| Output $ / M tokens | $180 | $1.20 |
| Results tracked | 16 | 21 |
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-M2: 39.3 (#159)
| Benchmark | GPT-5.4 Pro | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1370 |
Agentic & Tool Use Not comparable
GPT-5.4 Pro: —, MiniMax-M2: 25.1 (#109)
| Benchmark | GPT-5.4 Pro | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), MiniMax-M2: 19.4 (#258)
| Benchmark | GPT-5.4 Pro | MiniMax-M2 |
|---|---|---|
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1357 |
| Epoch Capabilities Index | 158.93 | — |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), MiniMax-M2: 37.3 (#160)
| Benchmark | GPT-5.4 Pro | MiniMax-M2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| LMArena Math | — | 1352 |
| 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-M2: 37.0 (#163)
| Benchmark | GPT-5.4 Pro | MiniMax-M2 |
|---|---|---|
| GPQA Diamond | 94.6% | — |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1337 |
Multilingual Not comparable
GPT-5.4 Pro: —, MiniMax-M2: 45.3 (#171)
| Benchmark | GPT-5.4 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | — | 1313 |
| LMArena Chinese | — | 1366 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1326 |
Instruction Following Not comparable
GPT-5.4 Pro: —, MiniMax-M2: 70.2 (#166)
| Benchmark | GPT-5.4 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | — | 1328 |
Long Context Not comparable
GPT-5.4 Pro: —, MiniMax-M2: 40.5 (#153)
| Benchmark | GPT-5.4 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1331 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, MiniMax-M2: 53.0 (#162)
| Benchmark | GPT-5.4 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1286 |
| LMArena Multi-Turn | — | 1361 |
Frequently asked questions
Is GPT-5.4 Pro better than MiniMax-M2?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 37.4 on the Noometry Index. MiniMax-M2 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-M2?
MiniMax-M2 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-M2 better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 39.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 205K.
How many benchmarks do GPT-5.4 Pro and MiniMax-M2 share?
0 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and MiniMax-M2 has 21.