Model comparison
Gemini 3.1 Flash Lite vs Tulu 3 (Tülu 3) 70B
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.4 to 32.6 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 3.1 Flash Lite scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.1 Flash Lite leads 39.5 to 13.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for Gemini 3.1 Flash Lite 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 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 40.4 | 32.6 |
| Released | 2026-03-03 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 38 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 37.5 (#179), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1400 | 1236 |
| LMArena WebDev | 1256 | — |
| SciCode | 41.9% | — |
| WeirdML | 52.2% | — |
| ALE-Bench | 797.73 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Flash Lite: 29.9 (#72), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| DeepResearch Bench | 37.3% | — |
Reasoning Too close to call
Gemini 3.1 Flash Lite: 22.3 (#181), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1407 | 1220 |
| Kagi LLM Benchmark | 67.2% | — |
| NYT Connections (extended) | 8.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| DTBench | 76.8% | — |
| LMCA | 35% | — |
| Epoch Capabilities Index | 144.45 | — |
| ForecastBench | 54.4 | — |
Math Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 39.5 (#82), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 4.4% |
| LMArena Math | 1427 | 1242 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
| MATH Level 5 | — | 42.7% |
Knowledge Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 41.7 (#95), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 81.8% | 46.3% |
| Humanity's Last Exam | 8.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| LMArena Expert | 1397 | — |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 38.7 (#57), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 52.5 (#82), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1410 | 1236 |
| LMArena Chinese | 1461 | 1249 |
| LMArena Russian | 1420 | 1246 |
| LMArena French | 1423 | — |
| LMArena German | 1429 | — |
| LMArena Japanese | 1411 | — |
| LMArena Korean | 1393 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 72.9 (#126), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1376 | 1233 |
Long Context Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 42.5 (#117), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1394 | 1224 |
Writing & Preference Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 61.0 (#90), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Gemini 3.1 Flash Lite | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1416 | 1256 |
| LMArena Creative Writing | 1401 | 1231 |
| LMArena Multi-Turn | 1417 | 1252 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Tulu 3 (Tülu 3) 70B?
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.4 to 32.6 on the Noometry Index.
Is Gemini 3.1 Flash Lite or Tulu 3 (Tülu 3) 70B better for coding?
Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.5 versus 35.4 in the Noometry coding category.
How many benchmarks do Gemini 3.1 Flash Lite and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.