Model comparison
Gemini 1.5 Pro (May 2024) vs Tulu 3 (Tülu 3) 70B
Gemini 1.5 Pro (May 2024) and Tulu 3 (Tülu 3) 70B score almost the same on the Noometry Index (31.9 vs 32.6), so choose on price, context window or the category you care about most.
Last verified . 14 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 6 categories and Tulu 3 (Tülu 3) 70B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 1.5 Pro (May 2024) leads 24.4 to 13.3.
- The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 42.7% for Tulu 3 (Tülu 3) 70B.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 31.9 | 32.6 |
| Released | 2024-02-15 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Gemini 1.5 Pro (May 2024): 33.8 (#239), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1294 | 1236 |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| 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), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Gemini 1.5 Pro (May 2024): 12.3 (#332), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1220 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |
| Epoch Capabilities Index | 131.73 | — |
| ForecastBench | 58.4 | — |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 24.4 (#260), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 4.4% |
| LMArena Math | 1315 | 1242 |
| MATH Level 5 | 70.4% | 42.7% |
| Omni-MATH | 36.4% | — |
Knowledge Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 29.3 (#228), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 57.2% | 46.3% |
| 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), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.5 (#169), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1312 | 1236 |
| LMArena Chinese | 1331 | 1249 |
| LMArena Russian | 1320 | 1246 |
| LMArena French | 1301 | — |
| LMArena German | 1286 | — |
| LMArena Japanese | 1292 | — |
| LMArena Korean | 1298 | — |
| LMArena Spanish | 1310 | — |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.8 (#180), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1233 |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.7 (#164), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1308 | 1224 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.5 (#167), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Gemini 1.5 Pro (May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1319 | 1256 |
| LMArena Creative Writing | 1333 | 1231 |
| LMArena Multi-Turn | 1296 | 1252 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Tulu 3 (Tülu 3) 70B?
Gemini 1.5 Pro (May 2024) and Tulu 3 (Tülu 3) 70B score almost the same on the Noometry Index (31.9 vs 32.6), so choose on price, context window or the category you care about most.
Is Gemini 1.5 Pro (May 2024) or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 33.8 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.