Model comparison
GPT-3.5-turbo vs Mistral Small 3.1
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 23.2 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Mistral Small 3.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Small 3.1 leads 38.3 to 23.9.
- The biggest single-benchmark swing is GPQA Diamond: 28% for GPT-3.5-turbo and 41.9% for Mistral Small 3.1.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $0.50 / $1.50 for GPT-3.5-turbo.
- Mistral Small 3.1 accepts more context: 128K tokens versus 16K.
- Mistral Small 3.1 has downloadable open weights; the other is API-only.
Side by side
| GPT-3.5-turbo | Mistral Small 3.1 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 23.2 | 31.7 |
| Released | 2023-03-01 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 16K | 128K |
| Max output | 4K | 102K |
| Input $ / M tokens | $0.50 | $0.35 |
| Output $ / M tokens | $1.50 | $0.56 |
| Results tracked | 44 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
GPT-3.5-turbo: 23.9 (#331), Mistral Small 3.1: 38.3 (#179)
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1136 | 1309 |
| 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 Small 3.1: —
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Mistral Small 3.1 leads
GPT-3.5-turbo: 13.8 (#332), Mistral Small 3.1: 19.7 (#254)
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| Chess Puzzles | 0% | 1% |
| LMArena Hard Prompts | 1108 | 1278 |
| Epoch Capabilities Index | 118.55 | 127.48 |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math Mistral Small 3.1 leads
GPT-3.5-turbo: 6.3 (#327), Mistral Small 3.1: 14.7 (#301)
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.2% | 3.9% |
| LMArena Math | 1142 | 1262 |
| FrontierMath (Tiers 1-3) | 0% | — |
| Omni-MATH | — | 24.8% |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Mistral Small 3.1 leads
GPT-3.5-turbo: 10.0 (#303), Mistral Small 3.1: 22.6 (#271)
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 28% | 41.9% |
| LMArena Expert | 1070 | 1257 |
| MMLU-Pro | — | 61% |
| GPQA (HELM) | — | 39.2% |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multimodal Not comparable
GPT-3.5-turbo: —, Mistral Small 3.1: 33.2 (#99)
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual Mistral Small 3.1 leads
GPT-3.5-turbo: 31.5 (#258), Mistral Small 3.1: 41.2 (#209)
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1108 | 1255 |
| LMArena Chinese | 1075 | 1253 |
| LMArena French | 1118 | 1273 |
| LMArena German | 1090 | 1266 |
| LMArena Japanese | 1043 | 1208 |
| LMArena Korean | 1019 | 1206 |
| LMArena Russian | 1123 | 1263 |
| LMArena Spanish | 1121 | 1283 |
Instruction Following Mistral Small 3.1 leads
GPT-3.5-turbo: 57.9 (#262), Mistral Small 3.1: 63.6 (#230)
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1119 | 1264 |
| IFEval | — | 75% |
Long Context Mistral Small 3.1 leads
GPT-3.5-turbo: 34.0 (#254), Mistral Small 3.1: 39.5 (#178)
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1121 | 1299 |
Writing & Preference Mistral Small 3.1 leads
GPT-3.5-turbo: 25.3 (#305), Mistral Small 3.1: 37.0 (#259)
| Benchmark | GPT-3.5-turbo | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1125 | 1277 |
| LMArena Creative Writing | 1092 | 1253 |
| EQ-Bench Creative Writing | 451 | 761 |
| LMArena Multi-Turn | 1117 | 1270 |
| WildBench | — | 78.8% |
Frequently asked questions
Is GPT-3.5-turbo better than Mistral Small 3.1?
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 23.2 on the Noometry Index.
Which is cheaper, GPT-3.5-turbo or Mistral Small 3.1?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; GPT-3.5-turbo lists at $0.50 and $1.50.
Is GPT-3.5-turbo or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
Mistral Small 3.1 does, with 128K tokens against 16K.
How many benchmarks do GPT-3.5-turbo and Mistral Small 3.1 share?
22 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Mistral Small 3.1 has 28.