Model comparison
Mistral Small 3 vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 87× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in writing & preference, where Nova Premier 1.0 leads 51.0 to 32.2.
- Mistral Small 3 is cheaper at $0.05 / $0.08 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 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | Nova Premier 1.0 | |
|---|---|---|
| Provider | Mistral AI | Amazon |
| Noometry Index | 31.2 | 38.3 |
| Released | 2025-01-30 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | 33K | 1M |
| Max output | 16K | 10K |
| Input $ / M tokens | $0.05 | $2.50 |
| Output $ / M tokens | $0.08 | $12.50 |
| Results tracked | 24 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Small 3: 36.5 (#207), Nova Premier 1.0: —
| Benchmark | Mistral Small 3 | Nova Premier 1.0 |
|---|---|---|
| BigCodeBench Instruct | 45.3% | — |
| LMArena Coding | 1246 | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Nova Premier 1.0 leads
Mistral Small 3: 18.9 (#273), Nova Premier 1.0: 23.0 (#185)
| Benchmark | Mistral Small 3 | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1233 | — |
| Epoch Capabilities Index | 127.07 | — |
Math Nova Premier 1.0 leads
Mistral Small 3: 16.3 (#295), Nova Premier 1.0: 33.8 (#199)
| Benchmark | Mistral Small 3 | Nova Premier 1.0 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| Omni-MATH | — | 35% |
| LMArena Math | 1240 | — |
Knowledge Nova Premier 1.0 leads
Mistral Small 3: 25.1 (#263), Nova Premier 1.0: 35.8 (#180)
| Benchmark | Mistral Small 3 | Nova Premier 1.0 |
|---|---|---|
| GPQA Diamond | 47.3% | — |
| MMLU-Pro | — | 72.6% |
| Confabulations | 25.2% | — |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1202 | — |
Multilingual Not comparable
Mistral Small 3: 37.3 (#236), Nova Premier 1.0: —
| Benchmark | Mistral Small 3 | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1198 | — |
| LMArena Chinese | 1204 | — |
| LMArena French | 1203 | — |
| LMArena German | 1211 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
| LMArena Russian | 1216 | — |
Instruction Following Nova Premier 1.0 leads
Mistral Small 3: 63.7 (#229), Nova Premier 1.0: 66.8 (#204)
| Benchmark | Mistral Small 3 | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1214 | — |
Long Context Not comparable
Mistral Small 3: 37.8 (#211), Nova Premier 1.0: —
| Benchmark | Mistral Small 3 | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1246 | — |
Writing & Preference Nova Premier 1.0 leads
Mistral Small 3: 32.2 (#280), Nova Premier 1.0: 51.0 (#178)
| Benchmark | Mistral Small 3 | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1234 | — |
| LMArena Creative Writing | 1195 | — |
| EQ-Bench Creative Writing | 707 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1217 | — |
Frequently asked questions
Is Mistral Small 3 better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 87× 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 3 or Nova Premier 1.0?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 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 33K.
How many benchmarks do Mistral Small 3 and Nova Premier 1.0 share?
0 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Nova Premier 1.0 has 6.