Model comparison
GPT-5.1 vs Mixtral 8x22B
GPT-5.1 is the stronger model overall, scoring 49.0 to 27.1 on the Noometry Index.
Last verified . 27 shared benchmarks.
Mistral AISummary
- They share 27 benchmarks with published results for both. GPT-5.1 scores higher in 9 categories and Mixtral 8x22B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.1 leads 50.6 to 15.1.
- The biggest single-benchmark swing is WeirdML: 60.8% for GPT-5.1 and 3.2% for Mixtral 8x22B.
- Mixtral 8x22B is cheaper at $2 / $6 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1 | Mixtral 8x22B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 49.0 | 27.1 |
| Released | 2025-11-13 | 2024-04-17 |
| Weights | Proprietary | Open |
| Context window | 400K | 64K |
| Max output | 128K | 64K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $10 | $6 |
| Results tracked | 63 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.4 (#66), Mixtral 8x22B: 24.2 (#329)
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 60.8% | 3.2% |
| LMArena Coding | 1454 | 1166 |
| SWE-bench Verified | 68% | — |
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1395 | — |
| SciCode | 43.3% | — |
| GSO | 13.7% | — |
| BigCodeBench Instruct | — | 40.6% |
| LiveBench Coding | 72.5% | — |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 1,192 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use GPT-5.1 leads
GPT-5.1: 32.7 (#60), Mixtral 8x22B: 23.1 (#127)
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 47.6% | — |
| Cybench | — | 7.5% |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1199 | — |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), Mixtral 8x22B: 19.9 (#248)
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1150 |
| DTBench | 90.1% | 55.1% |
| Epoch Capabilities Index | 149.64 | 122.03 |
| ForecastBench | 58.1 | 56.3 |
| ARC-AGI-2 | 17.6% | — |
| SimpleBench | 53.2% | — |
| ARC-AGI-1 | 72.8% | — |
| CritPt | 4.9% | — |
| Chess Puzzles | 32% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| Mystery Game Puzzles | 19% | — |
| LiveBench Data Analysis | 72.1% | — |
| LMCA | 43.9% | — |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), Mixtral 8x22B: 22.9 (#275)
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 46.4% | 16.3% |
| LMArena Math | 1447 | 1184 |
| OTIS Mock AIME 2024-2025 | 88.6% | — |
| LiveBench Math | 94.5% | — |
| MATH Level 5 | — | 24.2% |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5.1 leads
GPT-5.1: 50.6 (#71), Mixtral 8x22B: 15.1 (#293)
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 87.6% | 34.1% |
| MMLU-Pro | 57.9% | 46% |
| GPQA (HELM) | 44.2% | 33.4% |
| LMArena Expert | 1470 | 1113 |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| Vectara Hallucination Rate | 10.9% | — |
| MMLU | — | 77.8% |
Multimodal Not comparable
GPT-5.1: 44.8 (#19), Mixtral 8x22B: —
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1250 | — |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 53.8 (#56), Mixtral 8x22B: 32.8 (#255)
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1431 | 1128 |
| LMArena Chinese | 1495 | 1116 |
| LMArena French | 1450 | 1166 |
| LMArena German | 1438 | 1141 |
| LMArena Japanese | 1453 | 1037 |
| LMArena Korean | 1401 | 1057 |
| LMArena Russian | 1435 | 1158 |
| LMArena Spanish | 1433 | 1151 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Mixtral 8x22B: 57.7 (#266)
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| IFEval | 93.5% | 72.4% |
| LMArena Instruction Following | 1443 | 1147 |
| LiveBench Instruction Following | 93.3% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Mixtral 8x22B: 34.7 (#247)
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1447 | 1144 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), Mixtral 8x22B: 36.9 (#262)
| Benchmark | GPT-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1443 | 1162 |
| LMArena Creative Writing | 1427 | 1141 |
| WildBench | 86.3% | 71.1% |
| LMArena Multi-Turn | 1450 | 1130 |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Mixtral 8x22B?
GPT-5.1 is the stronger model overall, scoring 49.0 to 27.1 on the Noometry Index.
Which is cheaper, GPT-5.1 or Mixtral 8x22B?
Mixtral 8x22B is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or Mixtral 8x22B better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 64K.
How many benchmarks do GPT-5.1 and Mixtral 8x22B share?
27 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Mixtral 8x22B has 34.