Model comparison
GPT-3.5-turbo vs Pixtral Large
Pixtral Large is the stronger model overall, scoring 32.2 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 4.0× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. GPT-3.5-turbo scores higher in 0 categories and Pixtral Large in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Pixtral Large leads 21.7 to 13.8.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $2 / $6 for Pixtral Large.
- Pixtral Large accepts more context: 128K tokens versus 16K.
- Pixtral Large has downloadable open weights; the other is API-only.
Side by side
| GPT-3.5-turbo | Pixtral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 23.2 | 32.2 |
| Released | 2023-03-01 | 2024-11-01 |
| Weights | Proprietary | Open |
| Context window | 16K | 128K |
| Max output | 4K | 128K |
| Input $ / M tokens | $0.50 | $2 |
| Output $ / M tokens | $1.50 | $6 |
| Results tracked | 44 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-3.5-turbo: 23.9 (#331), Pixtral Large: —
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| LMArena Coding | 1136 | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Pixtral Large: —
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Pixtral Large leads
GPT-3.5-turbo: 13.8 (#332), Pixtral Large: 21.7 (#218)
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| Chess Puzzles | 0% | — |
| EnigmaEval | — | 0.8% |
| LMArena Hard Prompts | 1108 | — |
| 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 Not comparable
GPT-3.5-turbo: 6.3 (#327), Pixtral Large: —
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| LMArena Math | 1142 | — |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Not comparable
GPT-3.5-turbo: 10.0 (#303), Pixtral Large: —
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| GPQA Diamond | 28% | — |
| LMArena Expert | 1070 | — |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multimodal Not comparable
GPT-3.5-turbo: —, Pixtral Large: 30.6 (#111)
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| LMArena Vision | — | 1089 |
Multilingual Not comparable
GPT-3.5-turbo: 31.5 (#258), Pixtral Large: —
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| LMArena Non-English | 1108 | — |
| LMArena Chinese | 1075 | — |
| LMArena French | 1118 | — |
| LMArena German | 1090 | — |
| LMArena Japanese | 1043 | — |
| LMArena Korean | 1019 | — |
| LMArena Russian | 1123 | — |
| LMArena Spanish | 1121 | — |
Instruction Following Not comparable
GPT-3.5-turbo: 57.9 (#262), Pixtral Large: —
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| LMArena Instruction Following | 1119 | — |
Long Context Not comparable
GPT-3.5-turbo: 34.0 (#254), Pixtral Large: —
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| LMArena Longer Query | 1121 | — |
Writing & Preference Pixtral Large leads
GPT-3.5-turbo: 25.3 (#305), Pixtral Large: 32.9 (#278)
| Benchmark | GPT-3.5-turbo | Pixtral Large |
|---|---|---|
| EQ-Bench Creative Writing | 451 | 988 |
| LMArena Text | 1125 | — |
| LMArena Creative Writing | 1092 | — |
| LMArena Multi-Turn | 1117 | — |
Frequently asked questions
Is GPT-3.5-turbo better than Pixtral Large?
Pixtral Large is the stronger model overall, scoring 32.2 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 4.0× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Which is cheaper, GPT-3.5-turbo or Pixtral Large?
GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Pixtral Large lists at $2 and $6.
Which has the bigger context window?
Pixtral Large does, with 128K tokens against 16K.
How many benchmarks do GPT-3.5-turbo and Pixtral Large share?
1 benchmark has published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Pixtral Large has 3.