Model comparison
Mixtral 8x22B vs o3
o3 is the stronger model overall, scoring 47.5 to 27.1 on the Noometry Index.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and o3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 15.1.
- The biggest single-benchmark swing is MATH Level 5: 24.2% for Mixtral 8x22B and 97.8% for o3.
- Mixtral 8x22B is cheaper at $2 / $6 per million input/output tokens, against $2 / $8 for o3.
- o3 accepts more context: 200K tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x22B | o3 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 27.1 | 47.5 |
| Released | 2024-04-17 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 64K | 200K |
| Max output | 64K | 100K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $6 | $8 |
| Results tracked | 34 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Mixtral 8x22B: 24.2 (#329), o3: 46.8 (#64)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| WeirdML | 3.2% | 52.4% |
| LMArena Coding | 1166 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use o3 leads
Mixtral 8x22B: 23.1 (#127), o3: 34.5 (#44)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| Cybench | 7.5% | — |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Mixtral 8x22B: 19.9 (#248), o3: 32.0 (#78)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1402 |
| DTBench | 55.1% | 84.8% |
| Epoch Capabilities Index | 122.03 | 146.86 |
| ForecastBench | 56.3 | 62.5 |
| 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% |
| LMCA | — | 39.7% |
Math o3 leads
Mixtral 8x22B: 22.9 (#275), o3: 50.2 (#58)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| Omni-MATH | 16.3% | 71.4% |
| LMArena Math | 1184 | 1426 |
| MATH Level 5 | 24.2% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Mixtral 8x22B: 15.1 (#293), o3: 54.6 (#52)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| GPQA Diamond | 34.1% | 81.8% |
| MMLU-Pro | 46% | 85.9% |
| GPQA (HELM) | 33.4% | 75.3% |
| LMArena Expert | 1113 | 1402 |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| Confabulations | — | 14.4% |
| MMLU | 77.8% | — |
Multimodal Not comparable
Mixtral 8x22B: —, o3: 41.4 (#36)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
Mixtral 8x22B: 32.8 (#255), o3: 51.7 (#105)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| LMArena Non-English | 1128 | 1401 |
| LMArena Chinese | 1116 | 1437 |
| LMArena French | 1166 | 1430 |
| LMArena German | 1141 | 1420 |
| LMArena Japanese | 1037 | 1403 |
| LMArena Korean | 1057 | 1370 |
| LMArena Russian | 1158 | 1406 |
| LMArena Spanish | 1151 | 1395 |
Instruction Following o3 leads
Mixtral 8x22B: 57.7 (#266), o3: 72.8 (#127)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| IFEval | 72.4% | 86.9% |
| LMArena Instruction Following | 1147 | 1368 |
Long Context o3 leads
Mixtral 8x22B: 34.7 (#247), o3: 53.3 (#6)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| LMArena Longer Query | 1144 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Mixtral 8x22B: 36.9 (#262), o3: 63.5 (#64)
| Benchmark | Mixtral 8x22B | o3 |
|---|---|---|
| LMArena Text | 1162 | 1410 |
| LMArena Creative Writing | 1141 | 1359 |
| WildBench | 71.1% | 86.1% |
| LMArena Multi-Turn | 1130 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
Frequently asked questions
Is Mixtral 8x22B better than o3?
o3 is the stronger model overall, scoring 47.5 to 27.1 on the Noometry Index.
Which is cheaper, Mixtral 8x22B or o3?
Mixtral 8x22B is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; o3 lists at $2 and $8.
Is Mixtral 8x22B or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
o3 does, with 200K tokens against 64K.
How many benchmarks do Mixtral 8x22B and o3 share?
28 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and o3 has 63.