Model comparison
GPT-3.5-turbo vs Mistral
Mistral is the stronger model overall, scoring 29.9 to 23.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. GPT-3.5-turbo scores higher in 1 category and Mistral in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral leads 22.3 to 6.3.
Side by side
| GPT-3.5-turbo | Mistral | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 23.2 | 29.9 |
| Released | 2023-03-01 | — |
| Weights | Proprietary | Proprietary |
| Context window | 16K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 44 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
GPT-3.5-turbo: 23.9 (#331), Mistral: 33.8 (#250)
| Benchmark | GPT-3.5-turbo | Mistral |
|---|---|---|
| LMArena Coding | 1136 | 1162 |
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Mistral: —
| Benchmark | GPT-3.5-turbo | Mistral |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Mistral leads
GPT-3.5-turbo: 13.8 (#332), Mistral: 22.2 (#200)
| Benchmark | GPT-3.5-turbo | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1149 |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| Epoch Capabilities Index | 118.55 | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math Mistral leads
GPT-3.5-turbo: 6.3 (#327), Mistral: 22.3 (#278)
| Benchmark | GPT-3.5-turbo | Mistral |
|---|---|---|
| LMArena Math | 1142 | 1180 |
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| Omni-MATH | — | 7.2% |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Mistral leads
GPT-3.5-turbo: 10.0 (#303), Mistral: 16.6 (#288)
| Benchmark | GPT-3.5-turbo | Mistral |
|---|---|---|
| LMArena Expert | 1070 | 1125 |
| GPQA Diamond | 28% | — |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multilingual Mistral leads
GPT-3.5-turbo: 31.5 (#258), Mistral: 32.8 (#254)
| Benchmark | GPT-3.5-turbo | Mistral |
|---|---|---|
| LMArena Non-English | 1108 | 1129 |
| LMArena Chinese | 1075 | 1109 |
| LMArena French | 1118 | 1180 |
| LMArena German | 1090 | 1155 |
| LMArena Japanese | 1043 | 1013 |
| LMArena Korean | 1019 | 1032 |
| LMArena Russian | 1123 | 1168 |
| LMArena Spanish | 1121 | 1143 |
Instruction Following GPT-3.5-turbo leads
GPT-3.5-turbo: 57.9 (#262), Mistral: 52.6 (#288)
| Benchmark | GPT-3.5-turbo | Mistral |
|---|---|---|
| LMArena Instruction Following | 1119 | 1152 |
| IFEval | — | 56.8% |
Long Context Too close to call
GPT-3.5-turbo: 34.0 (#254), Mistral: 35.0 (#245)
| Benchmark | GPT-3.5-turbo | Mistral |
|---|---|---|
| LMArena Longer Query | 1121 | 1153 |
Writing & Preference Mistral leads
GPT-3.5-turbo: 25.3 (#305), Mistral: 37.0 (#260)
| Benchmark | GPT-3.5-turbo | Mistral |
|---|---|---|
| LMArena Text | 1125 | 1165 |
| LMArena Creative Writing | 1092 | 1158 |
| LMArena Multi-Turn | 1117 | 1147 |
| EQ-Bench Creative Writing | 451 | — |
| WildBench | — | 66% |
Frequently asked questions
Is GPT-3.5-turbo better than Mistral?
Mistral is the stronger model overall, scoring 29.9 to 23.2 on the Noometry Index.
Is GPT-3.5-turbo or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 23.9 in the Noometry coding category.
How many benchmarks do GPT-3.5-turbo and Mistral share?
17 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Mistral has 22.