Model comparison
GPT-5 vs Mixtral 8x22B
GPT-5 is the stronger model overall, scoring 50.9 to 26.7 on the Noometry Index.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. GPT-5 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 leads 56.5 to 15.1.
- The biggest single-benchmark swing is MATH Level 5: 98.1% for GPT-5 and 24.2% for Mixtral 8x22B.
- Mixtral 8x22B is cheaper at $2 / $6 per million input/output tokens, against $1.25 / $10 for GPT-5.
- GPT-5 accepts more context: 400K tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 | Mixtral 8x22B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 50.9 | 26.7 |
| Released | 2025-08-07 | 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 | 69 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
GPT-5: 50.7 (#39), Mixtral 8x22B: 23.8 (#324)
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 60.7% | 3.2% |
| LMArena Coding | 1436 | 1166 |
| SWE-bench Verified | 73.6% | — |
| SWE-bench Verified (bash only) | 65% | — |
| Aider Polyglot | 88% | — |
| LMArena WebDev | 1417 | — |
| SciCode | 42.9% | — |
| GSO | 6.9% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 1,162 | — |
| AlgoTune | 1.67 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use GPT-5 leads
GPT-5: 33.0 (#53), Mixtral 8x22B: 22.8 (#119)
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 49.6% | — |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| Cybench | — | 7.5% |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| LMArena Search | 1133 | — |
| METR Time Horizons | 69.6% | — |
Reasoning GPT-5 leads
GPT-5: 38.3 (#55), Mixtral 8x22B: 19.1 (#246)
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1415 | 1150 |
| DTBench | 90.7% | 55.1% |
| Epoch Capabilities Index | 150 | 122 |
| ForecastBench | 61.4 | 56.3 |
| ARC-AGI-2 | 9.9% | — |
| SimpleBench | 56.7% | — |
| Kagi LLM Benchmark | 72.7% | — |
| ARC-AGI-1 | 65.7% | — |
| CritPt | 12.6% | — |
| Chess Puzzles | 37% | — |
| EnigmaEval | 10.5% | — |
| EBR-Bench | 12.7% | — |
| Mystery Game Puzzles | 23% | — |
| LMCA | 40% | — |
Math GPT-5 leads
GPT-5: 54.6 (#36), Mixtral 8x22B: 21.2 (#271)
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 64.7% | 16.3% |
| LMArena Math | 1406 | 1184 |
| MATH Level 5 | 98.1% | 24.2% |
| FrontierMath (Tiers 1-3) | 55.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 91.4% | — |
| ProofBench | 18% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5 leads
GPT-5: 56.5 (#37), Mixtral 8x22B: 15.1 (#288)
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 86.2% | 34.1% |
| MMLU-Pro | 86.3% | 46% |
| GPQA (HELM) | 79.2% | 33.4% |
| LMArena Expert | 1420 | 1113 |
| Humanity's Last Exam | 25.3% | — |
| SimpleQA Verified | 50.1% | — |
| Confabulations | 10.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| MMLU | — | 77.8% |
Multimodal Not comparable
GPT-5: 46.1 (#12), Mixtral 8x22B: —
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1232 | — |
| GeoBench | 81% | — |
| VPCT | 66% | — |
Multilingual GPT-5 leads
GPT-5: 51.5 (#105), Mixtral 8x22B: 32.9 (#250)
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1397 | 1128 |
| LMArena Chinese | 1423 | 1116 |
| LMArena French | 1409 | 1165 |
| LMArena German | 1415 | 1141 |
| LMArena Japanese | 1411 | 1037 |
| LMArena Korean | 1361 | 1056 |
| LMArena Russian | 1406 | 1158 |
| LMArena Spanish | 1398 | 1150 |
Instruction Following GPT-5 leads
GPT-5: 74.0 (#107), Mixtral 8x22B: 57.9 (#261)
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| IFEval | 87.5% | 72.4% |
| LMArena Instruction Following | 1388 | 1147 |
Long Context GPT-5 leads
GPT-5: 69.5 (#2), Mixtral 8x22B: 34.6 (#242)
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1399 | 1144 |
| Fiction.LiveBench | 97.2% | — |
Writing & Preference GPT-5 leads
GPT-5: 63.5 (#63), Mixtral 8x22B: 37.1 (#257)
| Benchmark | GPT-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1406 | 1162 |
| LMArena Creative Writing | 1365 | 1141 |
| WildBench | 85.7% | 71.1% |
| LMArena Multi-Turn | 1426 | 1130 |
| Short-Story Creative Writing | 86% | — |
| EQ-Bench Creative Writing | 1627 | — |
Frequently asked questions
Is GPT-5 better than Mixtral 8x22B?
GPT-5 is the stronger model overall, scoring 50.9 to 26.7 on the Noometry Index.
Which is cheaper, GPT-5 or Mixtral 8x22B?
Mixtral 8x22B is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-5 lists at $1.25 and $10.
Is GPT-5 or Mixtral 8x22B better for coding?
GPT-5 scores higher on coding benchmarks: 50.7 versus 23.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5 does, with 400K tokens against 64K.
How many benchmarks do GPT-5 and Mixtral 8x22B share?
28 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and Mixtral 8x22B has 34.