Model comparison
Mixtral 8x22B vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 27.1 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AISummary
- They share 24 benchmarks with published results for both. Mixtral 8x22B scores higher in 2 categories and o3-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 15.1.
- The biggest single-benchmark swing is MATH Level 5: 24.2% for Mixtral 8x22B and 96.5% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- o3-mini accepts more context: 200K tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x22B | o3-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 27.1 | 36.7 |
| Released | 2024-04-17 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 64K | 200K |
| Max output | 64K | 100K |
| Input $ / M tokens | $2 | $1.10 |
| Output $ / M tokens | $6 | $4.40 |
| Results tracked | 34 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Mixtral 8x22B: 24.2 (#329), o3-mini: 40.8 (#132)
| Benchmark | Mixtral 8x22B | o3-mini |
|---|---|---|
| WeirdML | 3.2% | 43.7% |
| LMArena Coding | 1166 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| BigCodeBench Instruct | 40.6% | — |
| LiveBench Coding | — | 82.7% |
| BigCodeBench Complete | 50.2% | — |
| CadEval | — | 54% |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use o3-mini leads
Mixtral 8x22B: 23.1 (#127), o3-mini: 29.6 (#84)
| Benchmark | Mixtral 8x22B | o3-mini |
|---|---|---|
| Cybench | 7.5% | 22.5% |
Reasoning Mixtral 8x22B leads
Mixtral 8x22B: 19.9 (#248), o3-mini: 16.3 (#305)
| Benchmark | Mixtral 8x22B | o3-mini |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1366 |
| DTBench | 55.1% | 68.8% |
| Epoch Capabilities Index | 122.03 | 140.34 |
| ForecastBench | 56.3 | 59.6 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| LiveBench | — | 75.9% |
Math o3-mini leads
Mixtral 8x22B: 22.9 (#275), o3-mini: 28.1 (#244)
| Benchmark | Mixtral 8x22B | o3-mini |
|---|---|---|
| LMArena Math | 1184 | 1396 |
| MATH Level 5 | 24.2% | 96.5% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| Omni-MATH | 16.3% | — |
| LiveBench Math | — | 77.3% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Mixtral 8x22B: 15.1 (#293), o3-mini: 38.3 (#146)
| Benchmark | Mixtral 8x22B | o3-mini |
|---|---|---|
| GPQA Diamond | 34.1% | 77% |
| LMArena Expert | 1113 | 1364 |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 46% | — |
| Confabulations | — | 17.9% |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |
Multilingual o3-mini leads
Mixtral 8x22B: 32.8 (#255), o3-mini: 45.7 (#164)
| Benchmark | Mixtral 8x22B | o3-mini |
|---|---|---|
| LMArena Non-English | 1128 | 1319 |
| LMArena Chinese | 1116 | 1379 |
| LMArena French | 1166 | 1334 |
| LMArena German | 1141 | 1303 |
| LMArena Japanese | 1037 | 1286 |
| LMArena Korean | 1057 | 1314 |
| LMArena Russian | 1158 | 1304 |
| LMArena Spanish | 1151 | 1321 |
Instruction Following o3-mini leads
Mixtral 8x22B: 57.7 (#266), o3-mini: 75.1 (#72)
| Benchmark | Mixtral 8x22B | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1147 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
| IFEval | 72.4% | — |
Long Context Too close to call
Mixtral 8x22B: 34.7 (#247), o3-mini: 33.8 (#256)
| Benchmark | Mixtral 8x22B | o3-mini |
|---|---|---|
| LMArena Longer Query | 1144 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Mixtral 8x22B: 36.9 (#262), o3-mini: 50.3 (#182)
| Benchmark | Mixtral 8x22B | o3-mini |
|---|---|---|
| LMArena Text | 1162 | 1337 |
| LMArena Creative Writing | 1141 | 1286 |
| LMArena Multi-Turn | 1130 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| WildBench | 71.1% | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Mixtral 8x22B better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 27.1 on the Noometry Index.
Which is cheaper, Mixtral 8x22B or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Mixtral 8x22B or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
o3-mini does, with 200K tokens against 64K.
How many benchmarks do Mixtral 8x22B and o3-mini share?
24 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and o3-mini has 51.