Model comparison
Gemini 3.1 Pro Preview vs Sonar
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 38.5 on the Noometry Index. Sonar costs 4.5× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Google
PerplexitySummary
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 21.1.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 128K.
Side by side
| Gemini 3.1 Pro Preview | Sonar | |
|---|---|---|
| Provider | Perplexity | |
| Noometry Index | 56.7 | 38.5 |
| Released | 2026-02-19 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $2 | $1 |
| Output $ / M tokens | $12 | $1 |
| Results tracked | 71 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 42.5 (#99), Sonar: 35.7 (#221)
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| LMArena WebDev | 1447 | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1484 | — |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Pro Preview: 37.7 (#34), Sonar: —
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |
Reasoning Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.7 (#12), Sonar: 21.1 (#227)
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1485 | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 53.8% | — |
| Epoch Capabilities Index | 154.77 | — |
| ForecastBench | 59 | — |
| LiveBench | — | 46.9% |
Math Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 62.1 (#34), Sonar: 33.7 (#200)
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1485 | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |
Knowledge Not comparable
Gemini 3.1 Pro Preview: 71.8 (#3), Sonar: —
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |
| LMArena Expert | 1485 | — |
Multimodal Not comparable
Gemini 3.1 Pro Preview: 37.9 (#69), Sonar: —
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |
Multilingual Not comparable
Gemini 3.1 Pro Preview: 57.0 (#12), Sonar: —
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| LMArena Non-English | 1477 | — |
| LMArena Chinese | 1529 | — |
| LMArena French | 1487 | — |
| LMArena German | 1491 | — |
| LMArena Japanese | 1493 | — |
| LMArena Korean | 1455 | — |
| LMArena Russian | 1498 | — |
| LMArena Spanish | 1479 | — |
Instruction Following Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 77.0 (#32), Sonar: 71.4 (#150)
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1466 | — |
Long Context Not comparable
Gemini 3.1 Pro Preview: 47.4 (#18), Sonar: —
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |
| LMArena Longer Query | 1483 | — |
Writing & Preference Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 66.1 (#37), Sonar: 52.6 (#167)
| Benchmark | Gemini 3.1 Pro Preview | Sonar |
|---|---|---|
| LMArena Text | 1481 | — |
| LMArena Creative Writing | 1482 | — |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
| LMArena Multi-Turn | 1488 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than Sonar?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 38.5 on the Noometry Index. Sonar costs 4.5× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Pro Preview or Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.
Is Gemini 3.1 Pro Preview or Sonar better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Pro Preview does, with 1.05M tokens against 128K.
How many benchmarks do Gemini 3.1 Pro Preview and Sonar share?
0 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Sonar has 7.