Model comparison
Devstral Small 2505 vs Sonar
Sonar is the stronger model overall, scoring 37.8 to 33.9 on the Noometry Index. Devstral Small 2505 costs 6.7× 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 coding, where Devstral Small 2505 leads 38.6 to 35.1.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $1 / $1 for Sonar.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Sonar | |
|---|---|---|
| Provider | Mistral AI | Perplexity |
| Noometry Index | 33.9 | 37.8 |
| Released | 2025-05-07 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $0.10 | $1 |
| Output $ / M tokens | $0.30 | $1 |
| Results tracked | 4 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
Devstral Small 2505: 38.6 (#160), Sonar: 35.1 (#217)
| Benchmark | Devstral Small 2505 | Sonar |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LiveBench Coding | — | 35.1% |
Reasoning Sonar leads
Devstral Small 2505: 19.1 (#243), Sonar: 20.3 (#221)
| Benchmark | Devstral Small 2505 | Sonar |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 46.3% |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Not comparable
Devstral Small 2505: —, Sonar: 31.3 (#197)
| Benchmark | Devstral Small 2505 | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
Instruction Following Not comparable
Devstral Small 2505: —, Sonar: 71.5 (#146)
| Benchmark | Devstral Small 2505 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
Writing & Preference Not comparable
Devstral Small 2505: —, Sonar: 52.6 (#166)
| Benchmark | Devstral Small 2505 | Sonar |
|---|---|---|
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Devstral Small 2505 better than Sonar?
Sonar is the stronger model overall, scoring 37.8 to 33.9 on the Noometry Index. Devstral Small 2505 costs 6.7× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Sonar?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Sonar lists at $1 and $1.
Is Devstral Small 2505 or Sonar better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Devstral Small 2505 and Sonar share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Sonar has 7.