Model comparison
Gemini 1.5 Pro (May 2024) vs Sonar
Sonar is the stronger model overall, scoring 37.8 to 31.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Google
PerplexitySummary
- The widest gap is in reasoning, where Sonar leads 20.3 to 12.3.
Side by side
| Gemini 1.5 Pro (May 2024) | Sonar | |
|---|---|---|
| Provider | Perplexity | |
| Noometry Index | 31.9 | 37.8 |
| Released | 2024-02-15 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 45 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Gemini 1.5 Pro (May 2024): 33.8 (#239), Sonar: 35.1 (#217)
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1294 | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.8 (#137), Sonar: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Sonar leads
Gemini 1.5 Pro (May 2024): 12.3 (#332), Sonar: 20.3 (#221)
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1296 | — |
| DTBench | 59% | — |
| LiveBench Data Analysis | — | 37.9% |
| BIG-Bench Hard | 89.2% | — |
| Epoch Capabilities Index | 131.73 | — |
| ForecastBench | 58.4 | — |
| LiveBench | — | 46.9% |
Math Sonar leads
Gemini 1.5 Pro (May 2024): 24.4 (#260), Sonar: 31.3 (#197)
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| Omni-MATH | 36.4% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1315 | — |
| MATH Level 5 | 70.4% | — |
Knowledge Not comparable
Gemini 1.5 Pro (May 2024): 29.3 (#228), Sonar: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| GPQA Diamond | 57.2% | — |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| LMArena Expert | 1279 | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.2 (#72), Sonar: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Not comparable
Gemini 1.5 Pro (May 2024): 45.5 (#169), Sonar: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| LMArena Non-English | 1312 | — |
| LMArena Chinese | 1331 | — |
| LMArena French | 1301 | — |
| LMArena German | 1286 | — |
| LMArena Japanese | 1292 | — |
| LMArena Korean | 1298 | — |
| LMArena Russian | 1320 | — |
| LMArena Spanish | 1310 | — |
Instruction Following Sonar leads
Gemini 1.5 Pro (May 2024): 68.8 (#180), Sonar: 71.5 (#146)
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| IFEval | 83.7% | — |
| LMArena Instruction Following | 1297 | — |
Long Context Not comparable
Gemini 1.5 Pro (May 2024): 39.7 (#164), Sonar: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| LMArena Longer Query | 1308 | — |
Writing & Preference Too close to call
Gemini 1.5 Pro (May 2024): 52.5 (#167), Sonar: 52.6 (#166)
| Benchmark | Gemini 1.5 Pro (May 2024) | Sonar |
|---|---|---|
| LMArena Text | 1319 | — |
| LMArena Creative Writing | 1333 | — |
| WildBench | 81.3% | — |
| LMArena Multi-Turn | 1296 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Sonar?
Sonar is the stronger model overall, scoring 37.8 to 31.9 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.1 versus 33.8 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Sonar share?
0 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Sonar has 7.