Model comparison
Olmo 2 0325 32b Instruct vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 32.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)
PerplexitySummary
- The widest gap is in writing & preference, where Sonar leads 52.6 to 42.1.
- Olmo 2 0325 32b Instruct has downloadable open weights; the other is API-only.
Side by side
| Olmo 2 0325 32b Instruct | Sonar | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Perplexity |
| Noometry Index | 32.7 | 38.5 |
| Released | — | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 16 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Olmo 2 0325 32b Instruct: 35.2 (#227), Sonar: 35.7 (#221)
| Benchmark | Olmo 2 0325 32b Instruct | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1210 | — |
Reasoning Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 23.6 (#175), Sonar: 21.1 (#227)
| Benchmark | Olmo 2 0325 32b Instruct | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1208 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Sonar leads
Olmo 2 0325 32b Instruct: 26.8 (#255), Sonar: 33.7 (#200)
| Benchmark | Olmo 2 0325 32b Instruct | Sonar |
|---|---|---|
| Omni-MATH | 16.1% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1208 | — |
Knowledge Not comparable
Olmo 2 0325 32b Instruct: 19.5 (#279), Sonar: —
| Benchmark | Olmo 2 0325 32b Instruct | Sonar |
|---|---|---|
| MMLU-Pro | 41.4% | — |
| GPQA (HELM) | 28.7% | — |
Multilingual Not comparable
Olmo 2 0325 32b Instruct: 34.8 (#248), Sonar: —
| Benchmark | Olmo 2 0325 32b Instruct | Sonar |
|---|---|---|
| LMArena Non-English | 1160 | — |
| LMArena Chinese | 1192 | — |
| LMArena Russian | 1187 | — |
Instruction Following Sonar leads
Olmo 2 0325 32b Instruct: 61.5 (#244), Sonar: 71.4 (#150)
| Benchmark | Olmo 2 0325 32b Instruct | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| IFEval | 78% | — |
| LMArena Instruction Following | 1186 | — |
Long Context Not comparable
Olmo 2 0325 32b Instruct: 36.2 (#234), Sonar: —
| Benchmark | Olmo 2 0325 32b Instruct | Sonar |
|---|---|---|
| LMArena Longer Query | 1194 | — |
Writing & Preference Sonar leads
Olmo 2 0325 32b Instruct: 42.1 (#236), Sonar: 52.6 (#167)
| Benchmark | Olmo 2 0325 32b Instruct | Sonar |
|---|---|---|
| LMArena Text | 1218 | — |
| LMArena Creative Writing | 1199 | — |
| WildBench | 73.4% | — |
| LMArena Multi-Turn | 1221 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Olmo 2 0325 32b Instruct better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 32.7 on the Noometry Index.
Is Olmo 2 0325 32b Instruct or Sonar better for coding?
They score almost the same on coding (35.2 vs 35.7); test both on your own repository before choosing.
How many benchmarks do Olmo 2 0325 32b Instruct and Sonar share?
0 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Sonar has 7.