Model comparison
Gemini 3 Flash Preview vs Tulu 3 (Tülu 3) 70B
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 33.0 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. Gemini 3 Flash Preview 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 math, where Gemini 3 Flash Preview leads 51.7 to 14.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview 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 3 Flash Preview | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 52.3 | 33.0 |
| Released | 2025-12-17 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $3 | — |
| Results tracked | 59 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1460 | 1235 |
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |
| WeirdML | 61.6% | — |
| ALE-Bench | 1,367 | — |
Agentic & Tool Use Not comparable
Gemini 3 Flash Preview: 38.7 (#29), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1465 | 1220 |
| ARC-AGI-2 | 33.6% | — |
| SimpleBench | 61.1% | — |
| NYT Connections (extended) | 83.1% | — |
| ARC-AGI-1 | 84.7% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 89.1% | — |
| LMCA | 43.1% | — |
| Epoch Capabilities Index | 151.8 | — |
| ForecastBench | 58.5 | — |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 4.4% |
| LMArena Math | 1473 | 1242 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 15% | — |
| MATH Level 5 | — | 42.7% |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 89.4% | 46.3% |
| SimpleQA Verified | 66.8% | — |
| Vectara Hallucination Rate | 13.5% | — |
| LMArena Expert | 1462 | — |
Multimodal Not comparable
Gemini 3 Flash Preview: 45.5 (#16), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1458 | 1236 |
| LMArena Chinese | 1511 | 1249 |
| LMArena Russian | 1480 | 1246 |
| LMArena French | 1477 | — |
| LMArena German | 1497 | — |
| LMArena Japanese | 1489 | — |
| LMArena Korean | 1443 | — |
| LMArena Spanish | 1469 | — |
Instruction Following Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 75.7 (#56), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1437 | 1233 |
Long Context Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 44.4 (#67), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1452 | 1224 |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.5 (#45), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Gemini 3 Flash Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1466 | 1256 |
| LMArena Creative Writing | 1457 | 1231 |
| LMArena Multi-Turn | 1471 | 1252 |
Frequently asked questions
Is Gemini 3 Flash Preview better than Tulu 3 (Tülu 3) 70B?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 33.0 on the Noometry Index.
Is Gemini 3 Flash Preview or Tulu 3 (Tülu 3) 70B better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 36.0 in the Noometry coding category.
How many benchmarks do Gemini 3 Flash Preview and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.