Model comparison
Gemini 2.5 Pro vs Sonar
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 38.5 on the Noometry Index. Sonar costs 3.4× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Google
PerplexitySummary
- They share 7 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 4 categories and Sonar in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.5 Pro leads 63.7 to 52.6.
- The biggest single-benchmark swing is LiveBench Coding: 85.9% for Gemini 2.5 Pro and 35.1% for Sonar.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 128K.
Side by side
| Gemini 2.5 Pro | Sonar | |
|---|---|---|
| Provider | Perplexity | |
| Noometry Index | 45.0 | 38.5 |
| Released | 2025-03-25 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $1.25 | $1 |
| Output $ / M tokens | $10 | $1 |
| Results tracked | 78 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Pro leads
Gemini 2.5 Pro: 42.4 (#101), Sonar: 35.7 (#221)
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| LiveBench Coding | 85.9% | 35.1% |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| LMArena WebDev | 1227 | — |
| SciCode | 42.8% | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| LMArena Coding | 1452 | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Pro: 29.2 (#88), Sonar: —
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Gemini 2.5 Pro leads
Gemini 2.5 Pro: 28.8 (#99), Sonar: 21.1 (#227)
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| LiveBench Reasoning | 89.8% | 46.3% |
| LiveBench Data Analysis | 79.9% | 37.9% |
| LiveBench | 82.3% | 46.9% |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 62.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 41% | — |
| CritPt | 2% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| LMArena Hard Prompts | 1455 | — |
| DTBench | 82.4% | — |
| LMCA | 34.8% | — |
| Epoch Capabilities Index | 145.32 | — |
| ForecastBench | 61.3 | — |
Math Sonar leads
Gemini 2.5 Pro: 32.5 (#213), Sonar: 33.7 (#200)
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| LiveBench Math | 90.2% | 41.6% |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 84.7% | — |
| Omni-MATH | 41.6% | — |
| LMArena Math | 1450 | — |
| MATH Level 5 | 95.9% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Not comparable
Gemini 2.5 Pro: 56.0 (#46), Sonar: —
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| GPQA Diamond | 85.3% | — |
| Humanity's Last Exam | 21.6% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |
| LMArena Expert | 1452 | — |
Multimodal Not comparable
Gemini 2.5 Pro: 45.2 (#18), Sonar: —
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Not comparable
Gemini 2.5 Pro: 55.3 (#31), Sonar: —
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| LMArena Non-English | 1451 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1472 | — |
| LMArena German | 1487 | — |
| LMArena Japanese | 1461 | — |
| LMArena Korean | 1434 | — |
| LMArena Russian | 1461 | — |
| LMArena Spanish | 1473 | — |
Instruction Following Gemini 2.5 Pro leads
Gemini 2.5 Pro: 75.0 (#75), Sonar: 71.4 (#150)
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| LiveBench Instruction Following | 80.6% | 76.2% |
| IFEval | 84% | — |
| LMArena Instruction Following | 1437 | — |
Long Context Not comparable
Gemini 2.5 Pro: 59.8 (#5), Sonar: —
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| Fiction.LiveBench | 91.7% | — |
| LMArena Longer Query | 1449 | — |
Writing & Preference Gemini 2.5 Pro leads
Gemini 2.5 Pro: 63.7 (#62), Sonar: 52.6 (#167)
| Benchmark | Gemini 2.5 Pro | Sonar |
|---|---|---|
| LiveBench Language | 67.8% | 44.1% |
| LMArena Text | 1458 | — |
| LMArena Creative Writing | 1454 | — |
| Short-Story Creative Writing | 83.8% | — |
| EQ-Bench Creative Writing | 1421 | — |
| WildBench | 85.7% | — |
| LMArena Multi-Turn | 1453 | — |
Frequently asked questions
Is Gemini 2.5 Pro better than Sonar?
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 38.5 on the Noometry Index. Sonar costs 3.4× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Pro or Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.
Is Gemini 2.5 Pro or Sonar better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 128K.
How many benchmarks do Gemini 2.5 Pro and Sonar share?
7 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Sonar has 7.