Model comparison
GPT-4o mini vs Mixtral 8x7B
Mixtral 8x7B is the stronger model overall, scoring 27.1 to 25.5 on the Noometry Index. GPT-4o mini costs 2.7× less per token, which makes it the better buy when Mixtral 8x7B's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Mistral AISummary
- They share 31 benchmarks with published results for both. GPT-4o mini scores higher in 5 categories and Mixtral 8x7B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-4o mini leads 42.0 to 29.6.
- The biggest single-benchmark swing is MATH Level 5: 52.6% for GPT-4o mini and 10% for Mixtral 8x7B.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
- GPT-4o mini accepts more context: 128K tokens versus 32K.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | Mixtral 8x7B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 25.5 | 27.1 |
| Released | 2024-07-18 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 128K | 32K |
| Max output | 16K | 32K |
| Input $ / M tokens | $0.15 | $0.70 |
| Output $ / M tokens | $0.60 | $0.70 |
| Results tracked | 60 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mixtral 8x7B leads
GPT-4o mini: 22.0 (#335), Mixtral 8x7B: 32.8 (#269)
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1290 | 1126 |
| HumanEval+ | 83.5% | 39.6% |
| MBPP+ | 72.2% | 49.7% |
| Aider Polyglot | 3.6% | — |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.5 (#101), Mixtral 8x7B: —
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning Mixtral 8x7B leads
GPT-4o mini: 8.7 (#347), Mixtral 8x7B: 18.2 (#285)
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1115 |
| DTBench | 54.4% | 49.6% |
| Epoch Capabilities Index | 126.56 | 118.47 |
| PIQA | 88.7% | 83.6% |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| LiveBench | 41.3% | — |
| WinoGrande | — | 77.2% |
Math Mixtral 8x7B leads
GPT-4o mini: 10.4 (#314), Mixtral 8x7B: 18.8 (#289)
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| Omni-MATH | 28% | 10.5% |
| LMArena Math | 1267 | 1147 |
| MATH Level 5 | 52.6% | 10% |
| GSM8K | 91.3% | 74.4% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| LiveBench Math | 36.3% | — |
Knowledge GPT-4o mini leads
GPT-4o mini: 17.7 (#284), Mixtral 8x7B: 11.0 (#301)
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 37.7% | 30.6% |
| MMLU-Pro | 60.3% | 33.5% |
| GPQA (HELM) | 36.8% | 29.6% |
| LMArena Expert | 1235 | 1088 |
| MMLU | 81.8% | 70.6% |
| SimpleQA Verified | 8.3% | — |
| Confabulations | 37.2% | — |
| ARC (AI2) Challenge | — | 87.3% |
| BoolQ | 88.7% | — |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Mixtral 8x7B: —
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual GPT-4o mini leads
GPT-4o mini: 42.0 (#199), Mixtral 8x7B: 29.6 (#266)
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1266 | 1077 |
| LMArena Chinese | 1265 | 1055 |
| LMArena French | 1297 | 1166 |
| LMArena German | 1272 | 1114 |
| LMArena Japanese | 1216 | 931 |
| LMArena Korean | 1195 | 968 |
| LMArena Russian | 1275 | 1090 |
| LMArena Spanish | 1276 | 1111 |
Instruction Following GPT-4o mini leads
GPT-4o mini: 61.9 (#239), Mixtral 8x7B: 51.0 (#297)
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| IFEval | 78.2% | 57.5% |
| LMArena Instruction Following | 1258 | 1109 |
| LiveBench Instruction Following | 56.8% | — |
Long Context GPT-4o mini leads
GPT-4o mini: 39.1 (#186), Mixtral 8x7B: 33.4 (#260)
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1289 | 1103 |
Writing & Preference GPT-4o mini leads
GPT-4o mini: 39.5 (#248), Mixtral 8x7B: 34.2 (#270)
| Benchmark | GPT-4o mini | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1286 | 1132 |
| LMArena Creative Writing | 1268 | 1109 |
| WildBench | 79.1% | 67.3% |
| LMArena Multi-Turn | 1285 | 1115 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Mixtral 8x7B?
Mixtral 8x7B is the stronger model overall, scoring 27.1 to 25.5 on the Noometry Index. GPT-4o mini costs 2.7× less per token, which makes it the better buy when Mixtral 8x7B's lead doesn't matter for your workload.
Which is cheaper, GPT-4o mini or Mixtral 8x7B?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.
Is GPT-4o mini or Mixtral 8x7B better for coding?
Mixtral 8x7B scores higher on coding benchmarks: 32.8 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
GPT-4o mini does, with 128K tokens against 32K.
How many benchmarks do GPT-4o mini and Mixtral 8x7B share?
31 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Mixtral 8x7B has 38.