Model comparison
MiniMax M1 vs o3
o3 is the stronger model overall, scoring 47.5 to 40.3 on the Noometry Index. MiniMax M1 costs 3.6× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
MiniMaxSummary
- They share 18 benchmarks with published results for both. MiniMax M1 scores higher in 0 categories and o3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 36.4.
- The biggest single-benchmark swing is Fiction.LiveBench: 69.4% for MiniMax M1 and 88.9% for o3.
- MiniMax M1 is cheaper at $0.55 / $2.20 per million input/output tokens, against $2 / $8 for o3.
- MiniMax M1 accepts more context: 1M tokens versus 200K.
- MiniMax M1 has downloadable open weights; the other is API-only.
Side by side
| MiniMax M1 | o3 | |
|---|---|---|
| Provider | MiniMax | OpenAI |
| Noometry Index | 40.3 | 47.5 |
| Released | 2025-06-13 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 1M | 200K |
| Max output | 40K | 100K |
| Input $ / M tokens | $0.55 | $2 |
| Output $ / M tokens | $2.20 | $8 |
| Results tracked | 18 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
MiniMax M1: 39.9 (#153), o3: 46.8 (#64)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| LMArena Coding | 1359 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
MiniMax M1: —, o3: 34.5 (#44)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
MiniMax M1: 26.9 (#126), o3: 32.0 (#78)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| LMArena Hard Prompts | 1339 | 1402 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
Math o3 leads
MiniMax M1: 37.5 (#151), o3: 50.2 (#58)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| LMArena Math | 1361 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
MiniMax M1: 36.4 (#170), o3: 54.6 (#52)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| LMArena Expert | 1317 | 1402 |
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
Multimodal Not comparable
MiniMax M1: —, o3: 41.4 (#36)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
MiniMax M1: 45.8 (#163), o3: 51.7 (#105)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| LMArena Non-English | 1319 | 1401 |
| LMArena Chinese | 1360 | 1437 |
| LMArena French | 1370 | 1430 |
| LMArena German | 1350 | 1420 |
| LMArena Japanese | 1217 | 1403 |
| LMArena Korean | 1266 | 1370 |
| LMArena Russian | 1329 | 1406 |
| LMArena Spanish | 1353 | 1395 |
Instruction Following o3 leads
MiniMax M1: 69.3 (#174), o3: 72.8 (#127)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| LMArena Instruction Following | 1312 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
MiniMax M1: 41.4 (#141), o3: 53.3 (#6)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| Fiction.LiveBench | 69.4% | 88.9% |
| LMArena Longer Query | 1326 | 1372 |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
MiniMax M1: 53.1 (#161), o3: 63.5 (#64)
| Benchmark | MiniMax M1 | o3 |
|---|---|---|
| LMArena Text | 1343 | 1410 |
| LMArena Creative Writing | 1298 | 1359 |
| LMArena Multi-Turn | 1335 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is MiniMax M1 better than o3?
o3 is the stronger model overall, scoring 47.5 to 40.3 on the Noometry Index. MiniMax M1 costs 3.6× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, MiniMax M1 or o3?
MiniMax M1 is cheaper. It lists at $0.55 per million input tokens and $2.20 per million output tokens; o3 lists at $2 and $8.
Is MiniMax M1 or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
MiniMax M1 does, with 1M tokens against 200K.
How many benchmarks do MiniMax M1 and o3 share?
18 benchmarks have published results for both models. MiniMax M1 has 18 scored results on Noometry and o3 has 63.