Model comparison
Mistral Small vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 33.4 on the Noometry Index. Mistral Small costs 19× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Mistral Small scores higher in 1 category and Nova Premier 1.0 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Nova Premier 1.0 leads 33.8 to 16.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.8% for Mistral Small and 44.8% for Nova Premier 1.0.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- Nova Premier 1.0 accepts more context: 1M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral Small | Nova Premier 1.0 | |
|---|---|---|
| Provider | Mistral AI | Amazon |
| Noometry Index | 33.4 | 38.3 |
| Released | 2024-02-26 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 256K | 10K |
| Input $ / M tokens | $0.15 | $2.50 |
| Output $ / M tokens | $0.60 | $12.50 |
| Results tracked | 39 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Small: 34.0 (#247), Nova Premier 1.0: —
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| LMArena Coding | 1362 | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), Nova Premier 1.0: —
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Nova Premier 1.0 leads
Mistral Small: 19.8 (#250), Nova Premier 1.0: 23.0 (#185)
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 44.8% |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| LMArena Hard Prompts | 1335 | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| LiveBench | 44% | — |
Math Nova Premier 1.0 leads
Mistral Small: 16.4 (#293), Nova Premier 1.0: 33.8 (#199)
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| Omni-MATH | — | 35% |
| LiveBench Math | 39.9% | — |
| LMArena Math | 1341 | — |
| MATH Level 5 | 46.8% | — |
Knowledge Nova Premier 1.0 leads
Mistral Small: 31.0 (#222), Nova Premier 1.0: 35.8 (#180)
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| GPQA Diamond | 47.5% | — |
| MMLU-Pro | — | 72.6% |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1291 | — |
| MMLU | 68.7% | — |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Nova Premier 1.0: —
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Not comparable
Mistral Small: 45.5 (#169), Nova Premier 1.0: —
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1315 | — |
| LMArena Chinese | 1340 | — |
| LMArena French | 1337 | — |
| LMArena German | 1340 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1259 | — |
| LMArena Russian | 1324 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Too close to call
Mistral Small: 66.4 (#209), Nova Premier 1.0: 66.8 (#204)
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| LiveBench Instruction Following | 63.7% | — |
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1310 | — |
Long Context Not comparable
Mistral Small: 40.4 (#156), Nova Premier 1.0: —
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1327 | — |
Writing & Preference Mistral Small leads
Mistral Small: 52.5 (#171), Nova Premier 1.0: 51.0 (#178)
| Benchmark | Mistral Small | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1338 | — |
| LMArena Creative Writing | 1305 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1344 | — |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 33.4 on the Noometry Index. Mistral Small costs 19× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Which is cheaper, Mistral Small or Nova Premier 1.0?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Nova Premier 1.0 does, with 1M tokens against 262K.
How many benchmarks do Mistral Small and Nova Premier 1.0 share?
1 benchmark has published results for both models. Mistral Small has 39 scored results on Noometry and Nova Premier 1.0 has 6.