Model comparison
Ministral 8B vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 28.2 on the Noometry Index. Ministral 8B 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 39.6.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $1 / $1 for Sonar.
- Ministral 8B accepts more context: 262K tokens versus 128K.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Ministral 8B | Sonar | |
|---|---|---|
| Provider | Mistral AI | Perplexity |
| Noometry Index | 28.2 | 38.5 |
| Released | 2024-10-01 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 128K |
| Max output | 262K | 4K |
| Input $ / M tokens | $0.15 | $1 |
| Output $ / M tokens | $0.15 | $1 |
| Results tracked | 17 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Ministral 8B: 35.0 (#230), Sonar: 35.7 (#221)
| Benchmark | Ministral 8B | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1202 | — |
Agentic & Tool Use Not comparable
Ministral 8B: 16.4 (#148), Sonar: —
| Benchmark | Ministral 8B | Sonar |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Sonar leads
Ministral 8B: 18.4 (#281), Sonar: 21.1 (#227)
| Benchmark | Ministral 8B | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1191 | — |
| DTBench | 45.7% | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Sonar leads
Ministral 8B: 25.7 (#267), Sonar: 33.7 (#200)
| Benchmark | Ministral 8B | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |
Knowledge Not comparable
Ministral 8B: 12.6 (#297), Sonar: —
| Benchmark | Ministral 8B | Sonar |
|---|---|---|
| GPQA Diamond | 27.1% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1170 | — |
Multilingual Not comparable
Ministral 8B: 35.1 (#247), Sonar: —
| Benchmark | Ministral 8B | Sonar |
|---|---|---|
| LMArena Non-English | 1165 | — |
| LMArena Chinese | 1193 | — |
| LMArena Russian | 1195 | — |
Instruction Following Sonar leads
Ministral 8B: 60.5 (#250), Sonar: 71.4 (#150)
| Benchmark | Ministral 8B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1161 | — |
Long Context Not comparable
Ministral 8B: 36.7 (#227), Sonar: —
| Benchmark | Ministral 8B | Sonar |
|---|---|---|
| LMArena Longer Query | 1212 | — |
Writing & Preference Sonar leads
Ministral 8B: 39.6 (#246), Sonar: 52.6 (#167)
| Benchmark | Ministral 8B | Sonar |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1175 | — |
| LMArena Multi-Turn | 1166 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Ministral 8B better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 28.2 on the Noometry Index. Ministral 8B 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, Ministral 8B or Sonar?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Sonar lists at $1 and $1.
Is Ministral 8B or Sonar better for coding?
They score almost the same on coding (35.0 vs 35.7); test both on your own repository before choosing.
Which has the bigger context window?
Ministral 8B does, with 262K tokens against 128K.
How many benchmarks do Ministral 8B and Sonar share?
0 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Sonar has 7.