Model comparison
GPT-4 Turbo vs Mistral Nemo
GPT-4 Turbo is the stronger model overall, scoring 30.5 to 26.4 on the Noometry Index. Mistral Nemo costs 100× less per token, which makes it the better buy when GPT-4 Turbo's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. GPT-4 Turbo scores higher in 2 categories and Mistral Nemo in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4 Turbo leads 47.7 to 28.5.
- The biggest single-benchmark swing is MATH Level 5: 46.7% for GPT-4 Turbo and 10.8% for Mistral Nemo.
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Mistral Nemo has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Mistral Nemo | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 30.5 | 26.4 |
| Released | 2023-11-06 | 2024-07-01 |
| Weights | Proprietary | Open |
| Context window | 128K | 128K |
| Max output | 4K | 128K |
| Input $ / M tokens | $10 | $0.15 |
| Output $ / M tokens | $30 | $0.15 |
| Results tracked | 36 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-4 Turbo: 33.8 (#249), Mistral Nemo: —
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1268 | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Mistral Nemo: 23.5 (#125)
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.6% |
| BALROG | — | 17.6% |
| METR Time Horizons | 36.7% | — |
Reasoning Mistral Nemo leads
GPT-4 Turbo: 15.3 (#317), Mistral Nemo: 20.7 (#232)
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| DTBench | 61.6% | 48.6% |
| Epoch Capabilities Index | 127.25 | 118.68 |
| SimpleBench | 25.1% | — |
| Chess Puzzles | 6% | — |
| LMArena Hard Prompts | 1251 | — |
| LMCA | 9.8% | — |
| ForecastBench | 59.4 | — |
| PIQA | — | 83.5% |
Math Mistral Nemo leads
GPT-4 Turbo: 9.0 (#322), Mistral Nemo: 25.5 (#268)
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| MATH Level 5 | 46.7% | 10.8% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LMArena Math | 1272 | — |
| GSM8K | — | 84.2% |
Knowledge GPT-4 Turbo leads
GPT-4 Turbo: 24.3 (#268), Mistral Nemo: 12.3 (#298)
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| GPQA Diamond | 46.6% | 29.9% |
| Confabulations | 28.4% | — |
| LMArena Expert | 1223 | — |
| BoolQ | — | 82.5% |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.6 (#110), Mistral Nemo: —
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Not comparable
GPT-4 Turbo: 40.5 (#216), Mistral Nemo: —
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| LMArena Non-English | 1245 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1276 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
| LMArena Russian | 1259 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Not comparable
GPT-4 Turbo: 65.8 (#216), Mistral Nemo: —
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| LMArena Instruction Following | 1249 | — |
Long Context Not comparable
GPT-4 Turbo: 38.0 (#206), Mistral Nemo: —
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| LMArena Longer Query | 1254 | — |
Writing & Preference GPT-4 Turbo leads
GPT-4 Turbo: 47.7 (#206), Mistral Nemo: 28.5 (#296)
| Benchmark | GPT-4 Turbo | Mistral Nemo |
|---|---|---|
| LMArena Text | 1272 | — |
| LMArena Creative Writing | 1269 | — |
| EQ-Bench Creative Writing | — | 881 |
| LMArena Multi-Turn | 1267 | — |
Frequently asked questions
Is GPT-4 Turbo better than Mistral Nemo?
GPT-4 Turbo is the stronger model overall, scoring 30.5 to 26.4 on the Noometry Index. Mistral Nemo costs 100× less per token, which makes it the better buy when GPT-4 Turbo's lead doesn't matter for your workload.
Which is cheaper, GPT-4 Turbo or Mistral Nemo?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do GPT-4 Turbo and Mistral Nemo share?
4 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Mistral Nemo has 10.