LLMs TigerLive LLM benchmarks

Kimi K2 Thinking Turbo: benchmark scores, price and ranking

Kimi K2 Thinking Turbo from Moonshot ranks #187 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.5), based on 4 benchmark results captured up to 2026-10-13.

Organisation
Moonshot
Type
Open-weight / local model
Open weights
Yes
Aggregate rank
#187 of 743 (score 50.5)

Relative to other models, Kimi K2 Thinking Turbo is strongest on GPQA Diamond (#86 of 275) and weakest on WebDev Arena (#49 of 67).

Across the 4 benchmarks where at least ten models are scored, Kimi K2 Thinking Turbo is in the top 10% on 0 and in the top half on 3.

Kimi K2 Thinking Turbo benchmark results

Kimi K2 Thinking Turbo benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
GPQA Diamond84.2%#86 of 275Epoch AI Benchmarking Hub2026-10-13
OTIS Mock AIME83.1%#62 of 189Epoch AI Benchmarking Hub2026-10-13
Chess Puzzles20.0%#46 of 122Epoch AI Benchmarking Hub2026-10-13
WebDev Arena1,337#49 of 67Epoch AI Benchmarking Hub2026-10-13

About Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo is an open-weight model that can run on your own hardware from Moonshot. No API price is listed for it yet. We hold 4 benchmark results for it across 3 areas, and none is in the top tenth of its board.

Where Kimi K2 Thinking Turbo stands

On our aggregate score, Kimi K2 Thinking Turbo is #187 of 743 ranked models, around the middle of the table. Its score is 50.5; the scale is centred on 50, so it sits 0.5 points above the typical model. That beats 75% of the ranked field. Among the 13 ranked Moonshot models it is #4. The next one up is Kimi K2.5 at 50.7. The next one down is Kimi K2 Thinking (Together) at 49.7.

Kimi K2 Thinking Turbo, benchmark by benchmark

GPQA Diamond puts Kimi K2 Thinking Turbo at 84.2%, #86 of 275. That beats 69% of the models tested, but 11.6 points short of GPT-6 Astra (max) (95.8%). The results either side are Darwin-9B-NEG (84.3%) and Gemini 2.5 Pro Exp (Mar 2025) (83.8%). It covers expert-level science questions. The board median is 71.7%, so Kimi K2 Thinking Turbo is 12.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On OTIS Mock AIME, Kimi K2 Thinking Turbo reaches 83.1%. It ranks #62 of 189, ahead of 67% of the field, and 16.9 points behind Claude Fable 5.1 (max) at 100.0%. The results either side are GLM-4.7 (83.3%) and Gemma 4 26B A4B (82.2%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Kimi K2 Thinking Turbo is 25.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Kimi K2 Thinking Turbo manages 20.0% on Chess Puzzles, good for #46 of 122. GPT-6 Astra (max) leads at 72.0%, 52.0 points further up, and 62% of models sit below. The results either side are gpt-oss-120b (high) (20.0%) and Qwen 3.6 Flash (2026-04-16) (20.0%). It covers chess tactics puzzles. The board median is 12.5%, so Kimi K2 Thinking Turbo is 7.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Kimi K2 Thinking Turbo lands below the middle on WebDev Arena: 1,337, #49 of 67, with 72% of the field scoring higher. Claude Opus 5.5 (max) leads at 1,820; the closest result above is GPT-5.2 Codex at 1,339. It covers building web apps, crowd-voted (Elo). The board median is 1,433, so Kimi K2 Thinking Turbo is 96 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: solid, ahead of 68% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#86 of 275) and its weakest is OTIS Mock AIME (#62 of 189).

Reading these numbers

The 4 scores on this page come from 1 source: Epoch AI Benchmarking Hub (4). No official leaderboard supplied any of them, so treat them as third-party measurements. With 4 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

More from Moonshot

Compare it on the live leaderboard → · How the aggregate score works