Model comparison
Gemini 1.0 Pro vs Sonar
Sonar is the stronger model overall, scoring 37.8 to 27.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Google
PerplexitySummary
- The widest gap is in math, where Sonar leads 31.3 to 8.7.
Side by side
| Gemini 1.0 Pro | Sonar | |
|---|---|---|
| Provider | Perplexity | |
| Noometry Index | 27.1 | 37.8 |
| Released | 2023-12-13 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 24 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Gemini 1.0 Pro: 31.6 (#270), Sonar: 35.1 (#217)
| Benchmark | Gemini 1.0 Pro | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1108 | — |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Reasoning Sonar leads
Gemini 1.0 Pro: 16.4 (#292), Sonar: 20.3 (#221)
| Benchmark | Gemini 1.0 Pro | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1109 | — |
| DTBench | 45.9% | — |
| LiveBench Data Analysis | — | 37.9% |
| Epoch Capabilities Index | 116.97 | — |
| LiveBench | — | 46.9% |
Math Sonar leads
Gemini 1.0 Pro: 8.7 (#315), Sonar: 31.3 (#197)
| Benchmark | Gemini 1.0 Pro | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1132 | — |
| MATH Level 5 | 11.2% | — |
Knowledge Not comparable
Gemini 1.0 Pro: 15.5 (#286), Sonar: —
| Benchmark | Gemini 1.0 Pro | Sonar |
|---|---|---|
| GPQA Diamond | 34% | — |
| LMArena Expert | 1059 | — |
| MMLU | 70% | — |
Multilingual Not comparable
Gemini 1.0 Pro: 33.5 (#247), Sonar: —
| Benchmark | Gemini 1.0 Pro | Sonar |
|---|---|---|
| LMArena Non-English | 1138 | — |
| LMArena Chinese | 1124 | — |
| LMArena French | 1144 | — |
| LMArena German | 1125 | — |
| LMArena Japanese | 1023 | — |
| LMArena Russian | 1186 | — |
| LMArena Spanish | 1118 | — |
Instruction Following Sonar leads
Gemini 1.0 Pro: 57.9 (#262), Sonar: 71.5 (#146)
| Benchmark | Gemini 1.0 Pro | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1114 | — |
Long Context Not comparable
Gemini 1.0 Pro: 34.3 (#244), Sonar: —
| Benchmark | Gemini 1.0 Pro | Sonar |
|---|---|---|
| LMArena Longer Query | 1132 | — |
Writing & Preference Sonar leads
Gemini 1.0 Pro: 36.2 (#259), Sonar: 52.6 (#166)
| Benchmark | Gemini 1.0 Pro | Sonar |
|---|---|---|
| LMArena Text | 1149 | — |
| LMArena Creative Writing | 1130 | — |
| LMArena Multi-Turn | 1139 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Gemini 1.0 Pro better than Sonar?
Sonar is the stronger model overall, scoring 37.8 to 27.1 on the Noometry Index.
Is Gemini 1.0 Pro or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.1 versus 31.6 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Sonar share?
0 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Sonar has 7.