Model comparison
GPT-4o mini vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 25.5 on the Noometry Index. GPT-4o mini costs 2.0× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
MiniMaxSummary
- They share 16 benchmarks with published results for both. GPT-4o mini scores higher in 1 category and MiniMax-M2 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2 leads 37.3 to 10.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for GPT-4o mini and 57.8% for MiniMax-M2.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- MiniMax-M2 accepts more context: 205K tokens versus 128K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | MiniMax-M2 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 25.5 | 37.4 |
| Released | 2024-07-18 | 2025-10-27 |
| Weights | Proprietary | Open |
| Context window | 128K | 205K |
| Max output | 16K | 131K |
| Input $ / M tokens | $0.15 | $0.30 |
| Output $ / M tokens | $0.60 | $1.20 |
| Results tracked | 60 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
GPT-4o mini: 22.0 (#335), MiniMax-M2: 39.3 (#159)
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1290 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1297 |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use GPT-4o mini leads
GPT-4o mini: 27.5 (#101), MiniMax-M2: 25.1 (#109)
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| BALROG | 17.4% | — |
| Vending-Bench 2 | — | 160.6 |
Reasoning MiniMax-M2 leads
GPT-4o mini: 8.7 (#347), MiniMax-M2: 19.4 (#258)
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 57.8% |
| LMArena Hard Prompts | 1267 | 1357 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| NYT Connections (extended) | — | 14.8% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| Epoch Capabilities Index | 126.56 | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math MiniMax-M2 leads
GPT-4o mini: 10.4 (#314), MiniMax-M2: 37.3 (#160)
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1267 | 1352 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge MiniMax-M2 leads
GPT-4o mini: 17.7 (#284), MiniMax-M2: 37.0 (#163)
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1235 | 1337 |
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), MiniMax-M2: —
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual MiniMax-M2 leads
GPT-4o mini: 42.0 (#199), MiniMax-M2: 45.3 (#171)
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1266 | 1313 |
| LMArena Chinese | 1265 | 1366 |
| LMArena French | 1297 | 1335 |
| LMArena German | 1272 | 1355 |
| LMArena Russian | 1275 | 1331 |
| LMArena Spanish | 1276 | 1326 |
| LMArena Japanese | 1216 | — |
| LMArena Korean | 1195 | — |
Instruction Following MiniMax-M2 leads
GPT-4o mini: 61.9 (#239), MiniMax-M2: 70.2 (#166)
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1258 | 1328 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context MiniMax-M2 leads
GPT-4o mini: 39.1 (#186), MiniMax-M2: 40.5 (#153)
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1289 | 1331 |
Writing & Preference MiniMax-M2 leads
GPT-4o mini: 39.5 (#248), MiniMax-M2: 53.0 (#162)
| Benchmark | GPT-4o mini | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1286 | 1340 |
| LMArena Creative Writing | 1268 | 1286 |
| LMArena Multi-Turn | 1285 | 1361 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 25.5 on the Noometry Index. GPT-4o mini costs 2.0× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.
Which is cheaper, GPT-4o mini or MiniMax-M2?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.
Is GPT-4o mini or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 128K.
How many benchmarks do GPT-4o mini and MiniMax-M2 share?
16 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and MiniMax-M2 has 21.