Model comparison
Kimi K2 (Jul 2025) vs Kimi K2.5 Instant
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 41.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 2 categories and Kimi K2.5 Instant in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.5 Instant leads 29.7 to 23.3.
Side by side
| Kimi K2 (Jul 2025) | Kimi K2.5 Instant | |
|---|---|---|
| Provider | Moonshot AI | Moonshot AI |
| Noometry Index | 41.2 | 43.6 |
| Released | 2025-07-12 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.57 | — |
| Output $ / M tokens | $2.30 | — |
| Results tracked | 42 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Kimi K2 (Jul 2025): 42.4 (#102), Kimi K2.5 Instant: 42.6 (#97)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1399 | 1484 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1404 |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), Kimi K2.5 Instant: —
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Kimi K2.5 Instant leads
Kimi K2 (Jul 2025): 23.3 (#179), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1443 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1397 | 1442 |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2.5 Instant leads
Kimi K2 (Jul 2025): 37.3 (#157), Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1365 | 1440 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
Multimodal Not comparable
Kimi K2 (Jul 2025): —, Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual Kimi K2.5 Instant leads
Kimi K2 (Jul 2025): 49.6 (#130), Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1372 | 1406 |
| LMArena Chinese | 1415 | 1449 |
| LMArena French | 1379 | 1403 |
| LMArena German | 1387 | 1413 |
| LMArena Korean | 1325 | 1378 |
| LMArena Russian | 1385 | 1404 |
| LMArena Spanish | 1386 | 1447 |
| LMArena Japanese | 1349 | — |
Instruction Following Kimi K2.5 Instant leads
Kimi K2 (Jul 2025): 71.1 (#156), Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1348 | 1430 |
| IFEval | 85% | — |
Long Context Kimi K2.5 Instant leads
Kimi K2 (Jul 2025): 41.2 (#145), Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1353 | 1435 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.3 (#78), Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1380 | 1420 |
| LMArena Creative Writing | 1350 | 1381 |
| LMArena Multi-Turn | 1371 | 1427 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Kimi K2.5 Instant?
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 41.2 on the Noometry Index.
Is Kimi K2 (Jul 2025) or Kimi K2.5 Instant better for coding?
They score almost the same on coding (42.4 vs 42.6); test both on your own repository before choosing.
How many benchmarks do Kimi K2 (Jul 2025) and Kimi K2.5 Instant share?
16 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Kimi K2.5 Instant has 18.