kimi-k2-thinking
70±0
69interval70
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 37 min37 minutes ago
All sources syncing normally
- Arena · Text· 37 minutes ago
- Arena · WebDev· 37 minutes ago
- Arena · Vision· 37 minutes ago
- Arena · Agent· 37 minutes ago
- GPQA Diamond· 1 hour ago
- SWE-bench· 1 hour ago
- Terminal-Bench· 1 hour ago
- ARC-AGI-2· 1 hour ago
Filter by org:
Released:
moonshotai/Kimi-K2-Thinking
53±1
51interval54
kimi-k2-thinking-turbo
50±2
48interval53
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | Interval | Swing | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | Add to compare | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 35 | kimi-k2-thinking | Moonshot AI | Nov 2025 | $0.60 / $2.50 | 69.9 84.8Ranked 69.9 = (4 × 84.8 + 3 × 50) ÷ 7. 84.8 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | 21 | 4/22 | #35–209 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 75 | — | — | — | 90 | 96 | 79 | — | ||
| 336 | moonshotai/Kimi-K2-Thinking | Moonshot | — | — | 52.7 60.9Ranked 52.7 = (1 × 60.9 + 3 × 50) ÷ 4. 60.9 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 51–54 | — | 1/22low | — | — | — | — | — | — | — | — | — | — | 61 | — | — | — | — | — | — | — | — | — | — | — | — | ||
| 407 | kimi-k2-thinking-turbo | moonshot | Nov 2025 | — | 50.3 50.5Ranked 50.3 = (5 × 50.5 + 3 × 50) ÷ 8. 50.5 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 48–53 | 55 | 5/22 | #99–407 | 74 | 19 | — | 34 | — | — | — | 67 | 59 | — | — | — | — | — | — | — | — | — | — | — | — | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model