# GPT-5-Codex vs Kimi K2 Thinking Turbo

> Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 37.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-kimi-k2-thinking-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5-Codex leads 41.9 to 38.1.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 37.3 | 45.4 |
| Rank | 190 | 63 |
| Context | 400K | — |
| Input $/M | $1.25 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5-Codex: 41.9 (#100)
- Kimi K2 Thinking Turbo: 38.1 (#166)

| Benchmark | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena WebDev | — | 1322 |
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1454 |

## Agentic & Tool Use

- GPT-5-Codex: 30.8 (#66)
- Kimi K2 Thinking Turbo: —

| Benchmark | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| Terminal-Bench | 44.3% | — |

## Reasoning

- GPT-5-Codex: 30.0 (#80)
- Kimi K2 Thinking Turbo: 31.4 (#72)

| Benchmark | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| Chess Puzzles | — | 20% |
| LMArena Hard Prompts | — | 1428 |

## Math

- GPT-5-Codex: —
- Kimi K2 Thinking Turbo: 45.5 (#62)

| Benchmark | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 83.1% |
| LMArena Math | — | 1429 |

## Knowledge

- GPT-5-Codex: —
- Kimi K2 Thinking Turbo: 50.9 (#64)

| Benchmark | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | — | 84.2% |
| LMArena Expert | — | 1439 |

## Multilingual

- GPT-5-Codex: —
- Kimi K2 Thinking Turbo: 51.6 (#104)

| Benchmark | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | — | 1398 |
| LMArena Chinese | — | 1457 |
| LMArena French | — | 1425 |
| LMArena German | — | 1390 |
| LMArena Japanese | — | 1356 |
| LMArena Korean | — | 1329 |
| LMArena Russian | — | 1390 |
| LMArena Spanish | — | 1407 |

## Instruction Following

- GPT-5-Codex: —
- Kimi K2 Thinking Turbo: 74.2 (#103)

| Benchmark | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | — | 1403 |

## Long Context

- GPT-5-Codex: —
- Kimi K2 Thinking Turbo: 43.2 (#99)

| Benchmark | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | — | 1415 |

## Writing & Preference

- GPT-5-Codex: —
- Kimi K2 Thinking Turbo: 60.2 (#99)

| Benchmark | GPT-5-Codex | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | — | 1415 |
| LMArena Creative Writing | — | 1373 |
| LMArena Multi-Turn | — | 1414 |

## FAQ

### Is GPT-5-Codex better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 37.3 on the Noometry Index.

### Is GPT-5-Codex or Kimi K2 Thinking Turbo better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 38.1 in the Noometry coding category.

### How many benchmarks do GPT-5-Codex and Kimi K2 Thinking Turbo share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Kimi K2 Thinking Turbo has 21.