Kimi K2.5 (Thinking)
1,437±5
1,432CI1,442
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 27 min27 minutes ago
All sources syncing normally
- Arena · Text· 2 hours ago
- Arena · WebDev· 2 hours ago
- Arena · Vision· 2 hours ago
- Arena · Agent· 2 hours ago
- GPQA Diamond· 27 minutes ago
- SWE-bench· 27 minutes ago
- Terminal-Bench· 27 minutes ago
- ARC-AGI-2· 27 minutes ago
Filter by org:
Released:
kimi-k2.5-thinking
1,436±5
1,431CI1,442
kimi-k2.5-instant
1,405±12
1,393CI1,417
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 | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 71 | Kimi K2.5 (Thinking) | moonshot | Jan 2026 | $0.50 / $2.50 | 1,437 | 1,432–1,442 | #70–446 | ||
| 72 | kimi-k2.5-thinking | moonshot | Sep 2026 | — | 1,436 | 1,431–1,442 | #68–225 | ||
| 83 | kimi-k2.5-instant | moonshot | Oct 2026 | — | 1,405 | 1,393–1,417 | #84–353 |
Showing WebDev Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.