Model comparison
Mistral Nemo vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 26.4 on the Noometry Index. Mistral Nemo 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 writing & preference, where Sonar leads 52.6 to 28.5.
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $1 / $1 for Sonar.
- Mistral Nemo has downloadable open weights; the other is API-only.
Side by side
| Mistral Nemo | Sonar | |
|---|---|---|
| Provider | Mistral AI | Perplexity |
| Noometry Index | 26.4 | 38.5 |
| Released | 2024-07-01 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $0.15 | $1 |
| Output $ / M tokens | $0.15 | $1 |
| Results tracked | 10 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Nemo: —, Sonar: 35.7 (#221)
| Benchmark | Mistral Nemo | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
Agentic & Tool Use Not comparable
Mistral Nemo: 23.5 (#125), Sonar: —
| Benchmark | Mistral Nemo | Sonar |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.6% | — |
| BALROG | 17.6% | — |
Reasoning Too close to call
Mistral Nemo: 20.7 (#232), Sonar: 21.1 (#227)
| Benchmark | Mistral Nemo | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| DTBench | 48.6% | — |
| LiveBench Data Analysis | — | 37.9% |
| Epoch Capabilities Index | 118.68 | — |
| LiveBench | — | 46.9% |
| PIQA | 83.5% | — |
Math Sonar leads
Mistral Nemo: 25.5 (#268), Sonar: 33.7 (#200)
| Benchmark | Mistral Nemo | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| MATH Level 5 | 10.8% | — |
| GSM8K | 84.2% | — |
Knowledge Not comparable
Mistral Nemo: 12.3 (#298), Sonar: —
| Benchmark | Mistral Nemo | Sonar |
|---|---|---|
| GPQA Diamond | 29.9% | — |
| BoolQ | 82.5% | — |
Instruction Following Not comparable
Mistral Nemo: —, Sonar: 71.4 (#150)
| Benchmark | Mistral Nemo | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
Writing & Preference Sonar leads
Mistral Nemo: 28.5 (#296), Sonar: 52.6 (#167)
| Benchmark | Mistral Nemo | Sonar |
|---|---|---|
| EQ-Bench Creative Writing | 881 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Mistral Nemo better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 26.4 on the Noometry Index. Mistral Nemo 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, Mistral Nemo or Sonar?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Sonar lists at $1 and $1.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Mistral Nemo and Sonar share?
0 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and Sonar has 7.