What are Kimi K2 Turbo's benchmark scores?

As of 25 Oct 2026, Kimi K2 Turbo (thinking effort) scores 54.8 ±6.6 on the BenchLeader Index, strongest in human preference (61) and weakest in coding (44). That rests on 7 independent benchmark results, and every score on this page links to its publisher.

How does Kimi K2 Turbo rank?

Kimi K2 Turbo (thinking effort) is #243 of 785 ranked configurations on 25 Oct 2026. 348 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was Kimi K2 Turbo released?

Moonshot AI released Kimi K2 Turbo on 6 Nov 2025.

Moonshot AI Compare with another model

Kimi K2 Turbo

Kimi K2 Turbo is a Moonshot AI proprietary model, released 6 Nov 2025. Its best configuration (thinking reasoning effort) ranks #243 of 785 on the BenchLeader Index at 54.8 ±6.6, in the upper half. The ± is the point: 348 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in human preference (61) and lowest in coding (44). Last measured 23 Oct 2026.

Blended price: –
Output speed: –
First answer: –
Context: –
Full answer: –
Cost per run: –
Released: 6 Nov 2025

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index55
Reasoning61
Coding44
Maths61
Human preference61

How its index has moved

8 Sept 2026 to 21 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	thinking	Source	Trend
GPQA Diamond	84.2%#98	Epoch AI Benchmarking Hub
Arena Hard Prompts	1453#107	Arena (LMArena)

Coding

Benchmark	thinking	Source	Trend
Arena Coding	1486#99	Arena (LMArena)
Arena WebDev	1323#117	Arena (LMArena)

Maths

Benchmark	thinking	Source	Trend
OTIS Mock AIME	83.1%#107	Epoch AI Benchmarking Hub
Arena Maths	1436#96	Arena (LMArena)

Instruction following

Benchmark	thinking	Source	Trend
Arena Instruction Followingnot in index	1418#109	Arena (LMArena)

Human preference

Benchmark	thinking	Source
Arena Text	1430#112	Arena (LMArena)
Arena Creative Writingnot in index	1391#118	Arena (LMArena)
Arena Multi-turnnot in index	1432#108	Arena (LMArena)
Arena Longer Queriesnot in index	1433#116	Arena (LMArena)

New this month

Questions people ask

What are Kimi K2 Turbo's benchmark scores?: As of 25 Oct 2026, Kimi K2 Turbo (thinking effort) scores 54.8 ±6.6 on the BenchLeader Index, strongest in human preference (61) and weakest in coding (44). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
How does Kimi K2 Turbo rank?: Kimi K2 Turbo (thinking effort) is #243 of 785 ranked configurations on 25 Oct 2026. 348 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Kimi K2 Turbo released?: Moonshot AI released Kimi K2 Turbo on 6 Nov 2025.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Kimi K2 Turbo: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/kimi-k2-turbo.