Kimi K2.5 (instant): benchmark scores, price and ranking
Kimi K2.5 (instant) from Moonshot ranks #294 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.1), based on 1 benchmark results captured up to 2026-10-14.
- Organisation
- Moonshot
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2026-01-27 (source: epoch)
- Cheapest API price
- $0.450 in / $2.25 out per million tokens (via deepinfra, observed 2026-10-14T22:47Z)
- Aggregate rank
- #294 of 743 (score 49.1)
Across the 1 benchmark where at least ten models are scored, Kimi K2.5 (instant) is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $0.450 per million tokens, is lower than that of 52% of the 427 models with a listed price.
Kimi K2.5 (instant) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| WebDev Arena | 1,406 | #35 of 67 | Epoch AI Benchmarking Hub | 2026-10-14 |
About Kimi K2.5 (instant)
Kimi K2.5 (instant) is an open-weight model that can run on your own hardware from Moonshot. It was released on 2026-01-27, according to Epoch AI. The cheapest API listing we track charges $0.450 per million input tokens and $2.25 per million output tokens, through deepinfra. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where Kimi K2.5 (instant) stands
On our aggregate score, Kimi K2.5 (instant) is #294 of 743 ranked models, around the middle of the table. Its score is 49.1; the scale is centred on 50, so it sits 0.9 points below the typical model. That beats 60% of the ranked field. Among the 13 ranked Moonshot models it is #7. The next one up is Kimi-K2-Instruct-0905 at 49.5. The next one down is kimi-k2-0711-preview at 49.1.
Kimi K2.5 (instant), benchmark by benchmark
Kimi K2.5 (instant) lands below the middle on WebDev Arena: 1,406, #35 of 67, with 51% of the field scoring higher. Claude Opus 5.5 (max) leads at 1,820; the closest result above is mimo-v2-pro at 1,433. It covers building web apps, crowd-voted (Elo). The board median is 1,433, so Kimi K2.5 (instant) is 28 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Kimi K2.5 (instant) costs less than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4.1 Flash (high) ($0.010, 49.7), Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4 Flash 0731 (max) ($0.016, 53.0). Similar scores cost more on Kimi-K2-Instruct-0905 ($0.500) and Gemini 3 Flash Preview (High) ($0.500).
Release history
The Moonshot model released before it was Kimi K2.5 (Fireworks) on 2026-01-27, which scores 52.8. The next one was Kimi K2.6 on 2026-04-20, at 48.3.
Reading these numbers
The 1 score on this page comes from 1 source: Epoch AI Benchmarking Hub (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #291 gemini-2.5-pro_32K (49.2)
- #292 gpt-5-chat (49.2)
- #293 Claude Code + Qwen3.8-Max-0902 (49.1)
- #295 kimi-k2-0711-preview (49.1)
- #296 Claude Opus 4.1 (unknown thinking) (49.1)
- #297 TTS(Bo8) (49.1)
More from Moonshot
- Kimi K3 (max) (#15, 55.6)
- Kimi K2.5 (Fireworks) (#53, 52.8)
- Kimi K2.5 (#178, 50.6)
- Kimi K2 Thinking Turbo (#192, 50.4)
- Kimi K2 Thinking (Together) (#240, 49.7)
- Kimi-K2-Instruct-0905 (#257, 49.5)
Compare it on the live leaderboard → · How the aggregate score works