Model comparison
GPT-5.3 Chat vs Tulu 3 (Tülu 3) 70B
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. GPT-5.3 Chat 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 GPT-5.3 Chat leads 38.2 to 14.2.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Chat | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 42.8 | 33.0 |
| Released | 2026-03-03 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 18 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Chat leads
GPT-5.3 Chat: 41.4 (#124), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | GPT-5.3 Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1408 | 1235 |
Reasoning GPT-5.3 Chat leads
GPT-5.3 Chat: 28.5 (#102), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | GPT-5.3 Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1220 |
Math GPT-5.3 Chat leads
GPT-5.3 Chat: 38.2 (#142), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | GPT-5.3 Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1389 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge GPT-5.3 Chat leads
GPT-5.3 Chat: 38.8 (#140), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | GPT-5.3 Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1397 | — |
Multilingual GPT-5.3 Chat leads
GPT-5.3 Chat: 50.3 (#124), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | GPT-5.3 Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1382 | 1236 |
| LMArena Chinese | 1432 | 1249 |
| LMArena Russian | 1400 | 1246 |
| LMArena French | 1397 | — |
| LMArena German | 1384 | — |
| LMArena Japanese | 1352 | — |
| LMArena Korean | 1346 | — |
| LMArena Spanish | 1371 | — |
Instruction Following GPT-5.3 Chat leads
GPT-5.3 Chat: 72.8 (#129), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | GPT-5.3 Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1378 | 1233 |
Long Context GPT-5.3 Chat leads
GPT-5.3 Chat: 42.6 (#120), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | GPT-5.3 Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1396 | 1224 |
Writing & Preference GPT-5.3 Chat leads
GPT-5.3 Chat: 63.1 (#68), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | GPT-5.3 Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1389 | 1256 |
| LMArena Creative Writing | 1355 | 1231 |
| LMArena Multi-Turn | 1412 | 1252 |
| EQ-Bench Creative Writing | 1690 | — |
Frequently asked questions
Is GPT-5.3 Chat better than Tulu 3 (Tülu 3) 70B?
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 33.0 on the Noometry Index.
Is GPT-5.3 Chat or Tulu 3 (Tülu 3) 70B better for coding?
GPT-5.3 Chat scores higher on coding benchmarks: 41.4 versus 36.0 in the Noometry coding category.
How many benchmarks do GPT-5.3 Chat and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.