Model comparison
GPT-4o mini vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 25.5 on the Noometry Index. GPT-4o mini costs 2.0× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
MiniMaxSummary
- They share 21 benchmarks with published results for both. GPT-4o mini scores higher in 1 category and MiniMax-M2.5 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 22.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for GPT-4o mini and 55.2% for MiniMax-M2.5.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
- MiniMax-M2.5 accepts more context: 205K tokens versus 128K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | MiniMax-M2.5 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 25.5 | 38.3 |
| Released | 2024-07-18 | 2026-02-12 |
| 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 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
GPT-4o mini: 22.0 (#335), MiniMax-M2.5: 48.1 (#58)
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1290 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 618.17 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use MiniMax-M2.5 leads
GPT-4o mini: 27.5 (#101), MiniMax-M2.5: 30.4 (#77)
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| BALROG | 17.4% | — |
| Vending-Bench 2 | — | -23.16 |
Reasoning MiniMax-M2.5 leads
GPT-4o mini: 8.7 (#347), MiniMax-M2.5: 17.5 (#292)
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 0% | 4.9% |
| Kagi LLM Benchmark | 28.8% | 55.2% |
| LMArena Hard Prompts | 1267 | 1372 |
| Epoch Capabilities Index | 126.56 | 146.68 |
| SimpleBench | 10.7% | — |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math MiniMax-M2.5 leads
GPT-4o mini: 10.4 (#314), MiniMax-M2.5: 26.9 (#253)
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1267 | 1378 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| ProofBench | — | 4% |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge MiniMax-M2.5 leads
GPT-4o mini: 17.7 (#284), MiniMax-M2.5: 39.2 (#135)
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1235 | 1379 |
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| Vectara Hallucination Rate | — | 9.1% |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), MiniMax-M2.5: —
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual MiniMax-M2.5 leads
GPT-4o mini: 42.0 (#199), MiniMax-M2.5: 47.1 (#152)
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1266 | 1338 |
| LMArena Chinese | 1265 | 1393 |
| LMArena French | 1297 | 1362 |
| LMArena German | 1272 | 1362 |
| LMArena Japanese | 1216 | 1171 |
| LMArena Korean | 1195 | 1232 |
| LMArena Russian | 1275 | 1358 |
| LMArena Spanish | 1276 | 1354 |
Instruction Following MiniMax-M2.5 leads
GPT-4o mini: 61.9 (#239), MiniMax-M2.5: 71.5 (#148)
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1258 | 1353 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context GPT-4o mini leads
GPT-4o mini: 39.1 (#186), MiniMax-M2.5: 37.5 (#216)
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1289 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
GPT-4o mini: 39.5 (#248), MiniMax-M2.5: 53.9 (#153)
| Benchmark | GPT-4o mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1286 | 1359 |
| LMArena Creative Writing | 1268 | 1331 |
| EQ-Bench Creative Writing | 873 | 1361 |
| LMArena Multi-Turn | 1285 | 1364 |
| Short-Story Creative Writing | 67.2% | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 25.5 on the Noometry Index. GPT-4o mini costs 2.0× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.
Which is cheaper, GPT-4o mini or MiniMax-M2.5?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.
Is GPT-4o mini or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.5 does, with 205K tokens against 128K.
How many benchmarks do GPT-4o mini and MiniMax-M2.5 share?
21 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and MiniMax-M2.5 has 33.