# GPT-5-Codex vs Tulu 3 (Tülu 3) 70B

> GPT-5-Codex is the stronger model overall, scoring 37.3 to 32.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-tulu-3-70b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 22.9.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 37.3 | 32.6 |
| Rank | 190 | 242 |
| Context | 400K | — |
| Input $/M | $1.25 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5-Codex: 41.9 (#100)
- Tulu 3 (Tülu 3) 70B: 35.4 (#211)

| Benchmark | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1236 |

## Agentic & Tool Use

- GPT-5-Codex: 30.8 (#66)
- Tulu 3 (Tülu 3) 70B: —

| Benchmark | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Terminal-Bench | 44.3% | — |

## Reasoning

- GPT-5-Codex: 30.0 (#80)
- Tulu 3 (Tülu 3) 70B: 22.9 (#172)

| Benchmark | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| LMArena Hard Prompts | — | 1220 |

## Math

- GPT-5-Codex: —
- Tulu 3 (Tülu 3) 70B: 13.3 (#297)

| Benchmark | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |

## Knowledge

- GPT-5-Codex: —
- Tulu 3 (Tülu 3) 70B: 25.1 (#257)

| Benchmark | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |

## Multilingual

- GPT-5-Codex: —
- Tulu 3 (Tülu 3) 70B: 40.1 (#217)

| Benchmark | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |

## Instruction Following

- GPT-5-Codex: —
- Tulu 3 (Tülu 3) 70B: 65.0 (#222)

| Benchmark | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | — | 1233 |

## Long Context

- GPT-5-Codex: —
- Tulu 3 (Tülu 3) 70B: 37.1 (#217)

| Benchmark | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |

## Writing & Preference

- GPT-5-Codex: —
- Tulu 3 (Tülu 3) 70B: 45.8 (#218)

| Benchmark | GPT-5-Codex | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| LMArena Multi-Turn | — | 1252 |

## FAQ

### Is GPT-5-Codex better than Tulu 3 (Tülu 3) 70B?

GPT-5-Codex is the stronger model overall, scoring 37.3 to 32.6 on the Noometry Index.

### Is GPT-5-Codex or Tulu 3 (Tülu 3) 70B better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 35.4 in the Noometry coding category.

### How many benchmarks do GPT-5-Codex and Tulu 3 (Tülu 3) 70B share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.