Model comparison
Gemini 2.5 Pro vs Tulu 3 (Tülu 3) 70B
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 33.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 56.0 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84.7% for Gemini 2.5 Pro and 4.4% for Tulu 3 (Tülu 3) 70B.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 45.0 | 33.0 |
| Released | 2025-03-25 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 78 | 14 |
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), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1452 | 1235 |
| 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% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Pro: 29.2 (#88), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| 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), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1455 | 1220 |
| 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% | — |
| LiveBench Reasoning | 89.8% | — |
| DTBench | 82.4% | — |
| LiveBench Data Analysis | 79.9% | — |
| LMCA | 34.8% | — |
| Epoch Capabilities Index | 145.32 | — |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |
Math Gemini 2.5 Pro leads
Gemini 2.5 Pro: 32.5 (#213), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.7% | 4.4% |
| LMArena Math | 1450 | 1242 |
| MATH Level 5 | 95.9% | 42.7% |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 56.0 (#46), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 85.3% | 46.3% |
| 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), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.3 (#31), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1451 | 1236 |
| LMArena Chinese | 1507 | 1249 |
| LMArena Russian | 1461 | 1246 |
| LMArena French | 1472 | — |
| LMArena German | 1487 | — |
| LMArena Japanese | 1461 | — |
| LMArena Korean | 1434 | — |
| LMArena Spanish | 1473 | — |
Instruction Following Gemini 2.5 Pro leads
Gemini 2.5 Pro: 75.0 (#75), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1437 | 1233 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.8 (#5), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1449 | 1224 |
| Fiction.LiveBench | 91.7% | — |
Writing & Preference Gemini 2.5 Pro leads
Gemini 2.5 Pro: 63.7 (#62), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Gemini 2.5 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1458 | 1256 |
| LMArena Creative Writing | 1454 | 1231 |
| LMArena Multi-Turn | 1453 | 1252 |
| Short-Story Creative Writing | 83.8% | — |
| EQ-Bench Creative Writing | 1421 | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than Tulu 3 (Tülu 3) 70B?
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 33.0 on the Noometry Index.
Is Gemini 2.5 Pro or Tulu 3 (Tülu 3) 70B better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 36.0 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Pro and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.