Model comparison
Llama-3.3-70B-Instruct vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 30.6 on the Noometry Index.
Last verified . 14 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 5 categories and Tulu 3 (Tülu 3) 70B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Tulu 3 (Tülu 3) 70B leads 37.1 to 26.4.
Side by side
| Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 30.6 | 33.0 |
| Released | 2024-12-06 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.32 | — |
| Results tracked | 43 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Llama-3.3-70B-Instruct: 31.0 (#290), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1268 | 1235 |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| BigCodeBench Complete | 57.5% | — |
Agentic & Tool Use Not comparable
Llama-3.3-70B-Instruct: 25.8 (#105), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Llama-3.3-70B-Instruct: 14.1 (#327), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1220 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| Epoch Capabilities Index | 127.33 | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 15.3 (#298), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.1% | 4.4% |
| LMArena Math | 1267 | 1242 |
| MATH Level 5 | 41.6% | 42.7% |
| LiveBench Math | 42.2% | — |
Knowledge Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 30.6 (#226), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 47.4% | 46.3% |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| LMArena Expert | 1225 | — |
| MMLU | 86.3% | — |
Multilingual Too close to call
Llama-3.3-70B-Instruct: 39.9 (#220), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1236 | 1236 |
| LMArena Chinese | 1217 | 1249 |
| LMArena Russian | 1252 | 1246 |
| LMArena French | 1281 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1150 | — |
| LMArena Korean | 1143 | — |
| LMArena Spanish | 1270 | — |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.1 (#157), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1242 | 1233 |
| LiveBench Instruction Following | 82.7% | — |
Long Context Tulu 3 (Tülu 3) 70B leads
Llama-3.3-70B-Instruct: 26.4 (#295), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1256 | 1224 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 47.6 (#207), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Llama-3.3-70B-Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1274 | 1256 |
| LMArena Creative Writing | 1250 | 1231 |
| LMArena Multi-Turn | 1280 | 1252 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 30.6 on the Noometry Index.
Is Llama-3.3-70B-Instruct or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama-3.3-70B-Instruct and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.