Model comparison
Mixtral 8x22B vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 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 o4-mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o4-mini leads 43.6 to 15.1.
- The biggest single-benchmark swing is MATH Level 5: 24.2% for Mixtral 8x22B and 97.8% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- o4-mini accepts more context: 200K tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x22B | o4-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 27.1 | 41.6 |
| Released | 2024-04-17 | 2025-04-16 |
| 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 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Mixtral 8x22B: 24.2 (#329), o4-mini: 40.9 (#127)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| WeirdML | 3.2% | 52.6% |
| LMArena Coding | 1166 | 1368 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use o4-mini leads
Mixtral 8x22B: 23.1 (#127), o4-mini: 32.6 (#61)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| Cybench | 7.5% | — |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Mixtral 8x22B: 19.9 (#248), o4-mini: 24.6 (#162)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1351 |
| DTBench | 55.1% | 77.6% |
| Epoch Capabilities Index | 122.03 | 145.64 |
| ForecastBench | 56.3 | 61.8 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| LMCA | — | 26.5% |
Math o4-mini leads
Mixtral 8x22B: 22.9 (#275), o4-mini: 40.8 (#89)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| Omni-MATH | 16.3% | 72% |
| LMArena Math | 1184 | 1389 |
| MATH Level 5 | 24.2% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Mixtral 8x22B: 15.1 (#293), o4-mini: 43.6 (#91)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| GPQA Diamond | 34.1% | 79.6% |
| MMLU-Pro | 46% | 82% |
| GPQA (HELM) | 33.4% | 73.5% |
| LMArena Expert | 1113 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| MMLU | 77.8% | — |
Multimodal Not comparable
Mixtral 8x22B: —, o4-mini: 40.2 (#49)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
Mixtral 8x22B: 32.8 (#255), o4-mini: 47.0 (#154)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| LMArena Non-English | 1128 | 1337 |
| LMArena Chinese | 1116 | 1354 |
| LMArena French | 1166 | 1364 |
| LMArena German | 1141 | 1336 |
| LMArena Japanese | 1037 | 1308 |
| LMArena Korean | 1057 | 1312 |
| LMArena Russian | 1158 | 1334 |
| LMArena Spanish | 1151 | 1347 |
Instruction Following o4-mini leads
Mixtral 8x22B: 57.7 (#266), o4-mini: 75.2 (#68)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| IFEval | 72.4% | 92.8% |
| LMArena Instruction Following | 1147 | 1321 |
Long Context o4-mini leads
Mixtral 8x22B: 34.7 (#247), o4-mini: 45.5 (#33)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| LMArena Longer Query | 1144 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
Mixtral 8x22B: 36.9 (#262), o4-mini: 54.0 (#152)
| Benchmark | Mixtral 8x22B | o4-mini |
|---|---|---|
| LMArena Text | 1162 | 1353 |
| LMArena Creative Writing | 1141 | 1294 |
| WildBench | 71.1% | 85.4% |
| LMArena Multi-Turn | 1130 | 1350 |
| Short-Story Creative Writing | — | 75% |
Frequently asked questions
Is Mixtral 8x22B better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 27.1 on the Noometry Index.
Which is cheaper, Mixtral 8x22B or o4-mini?
o4-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 o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
o4-mini does, with 200K tokens against 64K.
How many benchmarks do Mixtral 8x22B and o4-mini share?
28 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and o4-mini has 60.