Model comparison
o3-mini vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 36.7 on the Noometry Index.
Last verified . 7 shared benchmarks.
PerplexitySummary
- They share 7 benchmarks with published results for both. o3-mini scores higher in 2 categories and Sonar in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Sonar leads 33.7 to 28.1.
- The biggest single-benchmark swing is LiveBench Coding: 82.7% for o3-mini and 35.1% for Sonar.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- o3-mini accepts more context: 200K tokens versus 128K.
Side by side
| o3-mini | Sonar | |
|---|---|---|
| Provider | OpenAI | Perplexity |
| Noometry Index | 36.7 | 38.5 |
| Released | 2024-12-20 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 128K |
| Max output | 100K | 4K |
| Input $ / M tokens | $1.10 | $1 |
| Output $ / M tokens | $4.40 | $1 |
| Results tracked | 51 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
o3-mini: 40.8 (#132), Sonar: 35.7 (#221)
| Benchmark | o3-mini | Sonar |
|---|---|---|
| LiveBench Coding | 82.7% | 35.1% |
| Aider Polyglot | 60.4% | — |
| SciCode | 39.8% | — |
| GSO | 1.3% | — |
| WeirdML | 43.7% | — |
| LMArena Coding | 1378 | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
o3-mini: 29.6 (#84), Sonar: —
| Benchmark | o3-mini | Sonar |
|---|---|---|
| Cybench | 22.5% | — |
Reasoning Sonar leads
o3-mini: 16.3 (#305), Sonar: 21.1 (#227)
| Benchmark | o3-mini | Sonar |
|---|---|---|
| LiveBench Reasoning | 89.6% | 46.3% |
| LiveBench Data Analysis | 70.6% | 37.9% |
| LiveBench | 75.9% | 46.9% |
| ARC-AGI-2 | 3% | — |
| SimpleBench | 22.8% | — |
| ARC-AGI-1 | 34.5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 17% | — |
| LMArena Hard Prompts | 1366 | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LMCA | 19% | — |
| Epoch Capabilities Index | 140.34 | — |
| ForecastBench | 59.6 | — |
Math Sonar leads
o3-mini: 28.1 (#244), Sonar: 33.7 (#200)
| Benchmark | o3-mini | Sonar |
|---|---|---|
| LiveBench Math | 77.3% | 41.6% |
| FrontierMath (Tiers 1-3) | 18.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 76.9% | — |
| LMArena Math | 1396 | — |
| MATH Level 5 | 96.5% | — |
| FrontierMath (Feb 2025 set) | 12.4% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Not comparable
o3-mini: 38.3 (#146), Sonar: —
| Benchmark | o3-mini | Sonar |
|---|---|---|
| GPQA Diamond | 77% | — |
| SimpleQA Verified | 15.3% | — |
| Confabulations | 17.9% | — |
| LMArena Expert | 1364 | — |
Multilingual Not comparable
o3-mini: 45.7 (#164), Sonar: —
| Benchmark | o3-mini | Sonar |
|---|---|---|
| LMArena Non-English | 1319 | — |
| LMArena Chinese | 1379 | — |
| LMArena French | 1334 | — |
| LMArena German | 1303 | — |
| LMArena Japanese | 1286 | — |
| LMArena Korean | 1314 | — |
| LMArena Russian | 1304 | — |
| LMArena Spanish | 1321 | — |
Instruction Following o3-mini leads
o3-mini: 75.1 (#72), Sonar: 71.4 (#150)
| Benchmark | o3-mini | Sonar |
|---|---|---|
| LiveBench Instruction Following | 84.4% | 76.2% |
| LMArena Instruction Following | 1337 | — |
Long Context Not comparable
o3-mini: 33.8 (#256), Sonar: —
| Benchmark | o3-mini | Sonar |
|---|---|---|
| Fiction.LiveBench | 50% | — |
| LMArena Longer Query | 1343 | — |
Writing & Preference Sonar leads
o3-mini: 50.3 (#182), Sonar: 52.6 (#167)
| Benchmark | o3-mini | Sonar |
|---|---|---|
| LiveBench Language | 50.7% | 44.1% |
| LMArena Text | 1337 | — |
| LMArena Creative Writing | 1286 | — |
| Short-Story Creative Writing | 61.7% | — |
| LMArena Multi-Turn | 1320 | — |
Frequently asked questions
Is o3-mini better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 36.7 on the Noometry Index.
Which is cheaper, o3-mini or Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is o3-mini or Sonar better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
o3-mini does, with 200K tokens against 128K.
How many benchmarks do o3-mini and Sonar share?
7 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Sonar has 7.