Model comparison
GPT-5.2 Pro vs Tulu 3 (Tülu 3) 70B
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 32.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- The widest gap is in math, where GPT-5.2 Pro leads 64.8 to 13.3.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Pro | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 52.2 | 32.6 |
| Released | 2025-12-11 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $21 | — |
| Output $ / M tokens | $168 | — |
| Results tracked | 8 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | GPT-5.2 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | — | 1236 |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.8 (#31), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | GPT-5.2 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| LMArena Hard Prompts | — | 1220 |
| Epoch Capabilities Index | 155.41 | — |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 64.8 (#23), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | GPT-5.2 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | GPT-5.2 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
Multilingual Not comparable
GPT-5.2 Pro: —, Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | GPT-5.2 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | GPT-5.2 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | — | 1233 |
Long Context Not comparable
GPT-5.2 Pro: —, Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | GPT-5.2 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | GPT-5.2 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is GPT-5.2 Pro better than Tulu 3 (Tülu 3) 70B?
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 32.6 on the Noometry Index.
How many benchmarks do GPT-5.2 Pro and Tulu 3 (Tülu 3) 70B share?
0 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.