Model comparison
Gemini 2.5 Pro vs Mistral Nemo
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 25.9 on the Noometry Index. Mistral Nemo costs 23× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Google
Mistral AISummary
- They share 6 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 5 categories and Mistral Nemo in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 55.8 to 12.3.
- The biggest single-benchmark swing is MATH Level 5: 95.9% for Gemini 2.5 Pro and 10.8% for Mistral Nemo.
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 128K.
- Mistral Nemo has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Pro | Mistral Nemo | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 44.9 | 25.9 |
| Released | 2025-03-25 | 2024-07-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 66K | 128K |
| Input $ / M tokens | $1.25 | $0.15 |
| Output $ / M tokens | $10 | $0.15 |
| Results tracked | 78 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 2.5 Pro: 42.8 (#86), Mistral Nemo: —
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| LMArena WebDev | 1227 | — |
| SciCode | 42.8% | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| LiveBench Coding | 85.9% | — |
| LMArena Coding | 1452 | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Gemini 2.5 Pro leads
Gemini 2.5 Pro: 29.1 (#81), Mistral Nemo: 23.3 (#118)
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| BALROG | 43.3% | 17.6% |
| Terminal-Bench | 32.6% | — |
| Berkeley Function Calling Leaderboard | — | 27.6% |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Gemini 2.5 Pro leads
Gemini 2.5 Pro: 28.8 (#85), Mistral Nemo: 19.9 (#230)
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| DTBench | 82.4% | 48.6% |
| Epoch Capabilities Index | 145.32 | 118.63 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 62.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 41% | — |
| CritPt | 2% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| LMArena Hard Prompts | 1455 | — |
| LiveBench Data Analysis | 79.9% | — |
| LMCA | 34.8% | — |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |
| PIQA | — | 83.5% |
Math Gemini 2.5 Pro leads
Gemini 2.5 Pro: 31.9 (#191), Mistral Nemo: 23.5 (#263)
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| MATH Level 5 | 95.9% | 10.8% |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 84.7% | — |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| LMArena Math | 1450 | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 84.2% |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.8 (#41), Mistral Nemo: 12.3 (#293)
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| GPQA Diamond | 85.3% | 29.9% |
| Humanity's Last Exam | 21.6% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |
| LMArena Expert | 1452 | — |
| BoolQ | — | 82.5% |
Multimodal Not comparable
Gemini 2.5 Pro: 44.5 (#16), Mistral Nemo: —
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Not comparable
Gemini 2.5 Pro: 55.5 (#30), Mistral Nemo: —
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| LMArena Non-English | 1452 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1473 | — |
| LMArena German | 1487 | — |
| LMArena Japanese | 1462 | — |
| LMArena Korean | 1435 | — |
| LMArena Russian | 1460 | — |
| LMArena Spanish | 1473 | — |
Instruction Following Not comparable
Gemini 2.5 Pro: 75.2 (#71), Mistral Nemo: —
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |
| LMArena Instruction Following | 1436 | — |
Long Context Not comparable
Gemini 2.5 Pro: 59.7 (#5), Mistral Nemo: —
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| Fiction.LiveBench | 91.7% | — |
| LMArena Longer Query | 1449 | — |
Writing & Preference Gemini 2.5 Pro leads
Gemini 2.5 Pro: 63.9 (#60), Mistral Nemo: 28.6 (#291)
| Benchmark | Gemini 2.5 Pro | Mistral Nemo |
|---|---|---|
| EQ-Bench Creative Writing | 1421 | 881 |
| LMArena Text | 1458 | — |
| LMArena Creative Writing | 1453 | — |
| Short-Story Creative Writing | 83.8% | — |
| WildBench | 85.7% | — |
| LMArena Multi-Turn | 1453 | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than Mistral Nemo?
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 25.9 on the Noometry Index. Mistral Nemo costs 23× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Pro or Mistral Nemo?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 128K.
How many benchmarks do Gemini 2.5 Pro and Mistral Nemo share?
6 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Mistral Nemo has 10.