Model comparison
GPT-4o mini vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 25.5 on the Noometry Index. GPT-4o mini costs 11× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Last verified . 44 shared benchmarks.
Mistral AISummary
- They share 44 benchmarks with published results for both. GPT-4o mini scores higher in 2 categories and Mistral Large in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Large leads 34.3 to 22.0.
- The biggest single-benchmark swing is BigCodeBench Complete: 57.4% for GPT-4o mini and 38.3% for Mistral Large.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 128K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 25.5 | 31.9 |
| Released | 2024-07-18 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 16K | 16K |
| Input $ / M tokens | $0.15 | $2 |
| Output $ / M tokens | $0.60 | $6 |
| Results tracked | 60 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
GPT-4o mini: 22.0 (#335), Mistral Large: 34.3 (#240)
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 46.1% | 30% |
| LiveBench Coding | 43.1% | 47.1% |
| LMArena Coding | 1290 | 1277 |
| BigCodeBench Complete | 57.4% | 38.3% |
| HumanEval+ | 83.5% | 62.2% |
| MBPP+ | 72.2% | 59.5% |
| Aider Polyglot | 3.6% | — |
| SciCode | — | 36.2% |
| WeirdML | 11.8% | — |
| ALE-Bench | — | 264.7 |
Agentic & Tool Use Mistral Large leads
GPT-4o mini: 27.5 (#101), Mistral Large: 28.6 (#89)
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| BALROG | 17.4% | — |
Reasoning Mistral Large leads
GPT-4o mini: 8.7 (#347), Mistral Large: 15.8 (#310)
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| SimpleBench | 10.7% | 22.5% |
| LiveBench Reasoning | 32.8% | 43.5% |
| LMArena Hard Prompts | 1267 | 1257 |
| DTBench | 54.4% | 65.1% |
| LiveBench Data Analysis | 50% | 50.1% |
| LMCA | 10.4% | 16.7% |
| Epoch Capabilities Index | 126.56 | 128.52 |
| LiveBench | 41.3% | 48.4% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 28.8% | — |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 12% | — |
| ForecastBench | — | 57.1 |
| PIQA | 88.7% | — |
Math Mistral Large leads
GPT-4o mini: 10.4 (#314), Mistral Large: 18.2 (#291)
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 8.5% |
| Omni-MATH | 28% | 28.1% |
| LiveBench Math | 36.3% | 42.5% |
| LMArena Math | 1267 | 1262 |
| MATH Level 5 | 52.6% | 50.3% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 91.3% | — |
Knowledge Mistral Large leads
GPT-4o mini: 17.7 (#284), Mistral Large: 30.1 (#230)
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| GPQA Diamond | 37.7% | 51.3% |
| MMLU-Pro | 60.3% | 59.9% |
| Confabulations | 37.2% | 21.4% |
| GPQA (HELM) | 36.8% | 43.5% |
| LMArena Expert | 1235 | 1232 |
| MMLU | 81.8% | 80% |
| SimpleQA Verified | 8.3% | — |
| Vectara Hallucination Rate | — | 4.5% |
| BoolQ | 88.7% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Mistral Large: —
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual GPT-4o mini leads
GPT-4o mini: 42.0 (#199), Mistral Large: 40.0 (#219)
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| LMArena Non-English | 1266 | 1237 |
| LMArena Chinese | 1265 | 1240 |
| LMArena French | 1297 | 1325 |
| LMArena German | 1272 | 1254 |
| LMArena Japanese | 1216 | 1188 |
| LMArena Korean | 1195 | 1202 |
| LMArena Russian | 1275 | 1257 |
| LMArena Spanish | 1276 | 1268 |
Instruction Following Mistral Large leads
GPT-4o mini: 61.9 (#239), Mistral Large: 67.9 (#191)
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| LiveBench Instruction Following | 56.8% | 67.9% |
| IFEval | 78.2% | 87.7% |
| LMArena Instruction Following | 1258 | 1249 |
Long Context Too close to call
GPT-4o mini: 39.1 (#186), Mistral Large: 38.3 (#199)
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1289 | 1261 |
Writing & Preference Mistral Large leads
GPT-4o mini: 39.5 (#248), Mistral Large: 40.7 (#242)
| Benchmark | GPT-4o mini | Mistral Large |
|---|---|---|
| LMArena Text | 1286 | 1266 |
| LMArena Creative Writing | 1268 | 1243 |
| Short-Story Creative Writing | 67.2% | 69% |
| EQ-Bench Creative Writing | 873 | 985 |
| WildBench | 79.1% | 80.1% |
| LMArena Multi-Turn | 1285 | 1260 |
| LiveBench Language | 28.6% | 39.4% |
Frequently asked questions
Is GPT-4o mini better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 25.5 on the Noometry Index. GPT-4o mini costs 11× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Which is cheaper, GPT-4o mini or Mistral Large?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mistral Large lists at $2 and $6.
Is GPT-4o mini or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 128K.
How many benchmarks do GPT-4o mini and Mistral Large share?
44 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Mistral Large has 51.