Model comparison
Mistral Small 3 vs Sonar
Sonar is the stronger model overall, scoring 37.8 to 30.9 on the Noometry Index. Mistral Small 3 costs 17× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AI
PerplexitySummary
- The widest gap is in writing & preference, where Sonar leads 52.6 to 32.4.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $1 / $1 for Sonar.
- Sonar accepts more context: 128K tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | Sonar | |
|---|---|---|
| Provider | Mistral AI | Perplexity |
| Noometry Index | 30.9 | 37.8 |
| Released | 2025-01-30 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 33K | 128K |
| Max output | 16K | 4K |
| Input $ / M tokens | $0.05 | $1 |
| Output $ / M tokens | $0.08 | $1 |
| Results tracked | 24 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Small 3: 36.0 (#203), Sonar: 35.1 (#217)
| Benchmark | Mistral Small 3 | Sonar |
|---|---|---|
| BigCodeBench Instruct | 45.3% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1246 | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Sonar leads
Mistral Small 3: 18.2 (#269), Sonar: 20.3 (#221)
| Benchmark | Mistral Small 3 | Sonar |
|---|---|---|
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1233 | — |
| LiveBench Data Analysis | — | 37.9% |
| Epoch Capabilities Index | 127.06 | — |
| LiveBench | — | 46.9% |
Math Sonar leads
Mistral Small 3: 15.3 (#290), Sonar: 31.3 (#197)
| Benchmark | Mistral Small 3 | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1240 | — |
Knowledge Not comparable
Mistral Small 3: 25.0 (#258), Sonar: —
| Benchmark | Mistral Small 3 | Sonar |
|---|---|---|
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
| LMArena Expert | 1202 | — |
Multilingual Not comparable
Mistral Small 3: 37.5 (#231), Sonar: —
| Benchmark | Mistral Small 3 | Sonar |
|---|---|---|
| LMArena Non-English | 1198 | — |
| LMArena Chinese | 1204 | — |
| LMArena French | 1202 | — |
| LMArena German | 1211 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
| LMArena Russian | 1216 | — |
Instruction Following Sonar leads
Mistral Small 3: 63.9 (#224), Sonar: 71.5 (#146)
| Benchmark | Mistral Small 3 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1214 | — |
Long Context Not comparable
Mistral Small 3: 37.8 (#206), Sonar: —
| Benchmark | Mistral Small 3 | Sonar |
|---|---|---|
| LMArena Longer Query | 1246 | — |
Writing & Preference Sonar leads
Mistral Small 3: 32.4 (#275), Sonar: 52.6 (#166)
| Benchmark | Mistral Small 3 | Sonar |
|---|---|---|
| LMArena Text | 1234 | — |
| LMArena Creative Writing | 1195 | — |
| EQ-Bench Creative Writing | 707 | — |
| LMArena Multi-Turn | 1217 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Mistral Small 3 better than Sonar?
Sonar is the stronger model overall, scoring 37.8 to 30.9 on the Noometry Index. Mistral Small 3 costs 17× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 3 or Sonar?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Sonar lists at $1 and $1.
Is Mistral Small 3 or Sonar better for coding?
They score almost the same on coding (36.0 vs 35.1); test both on your own repository before choosing.
Which has the bigger context window?
Sonar does, with 128K tokens against 33K.
How many benchmarks do Mistral Small 3 and Sonar share?
0 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Sonar has 7.