Model comparison
Grok-3 mini 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. Grok-3 mini scores higher in 3 categories and Kimi K2.5 Instant in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.5 Instant leads 29.7 to 13.6.
- Kimi K2.5 Instant has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Kimi K2.5 Instant | |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 41.2 | 43.6 |
| Released | 2025-04-09 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
Grok-3 mini: 40.8 (#131), Kimi K2.5 Instant: 42.6 (#97)
| Benchmark | Grok-3 mini | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1379 | 1484 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1404 |
| WeirdML | 42.6% | — |
Reasoning Kimi K2.5 Instant leads
Grok-3 mini: 13.6 (#334), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | Grok-3 mini | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1443 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | Grok-3 mini | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1386 | 1442 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | Grok-3 mini | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1395 | 1440 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multimodal Not comparable
Grok-3 mini: —, Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | Grok-3 mini | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual Kimi K2.5 Instant leads
Grok-3 mini: 48.1 (#145), Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | Grok-3 mini | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1352 | 1406 |
| LMArena Chinese | 1387 | 1449 |
| LMArena French | 1357 | 1403 |
| LMArena German | 1349 | 1413 |
| LMArena Korean | 1335 | 1378 |
| LMArena Russian | 1353 | 1404 |
| LMArena Spanish | 1381 | 1447 |
| LMArena Japanese | 1342 | — |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | Grok-3 mini | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1357 | 1430 |
| IFEval | 95.1% | — |
Long Context Kimi K2.5 Instant leads
Grok-3 mini: 41.0 (#147), Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | Grok-3 mini | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1372 | 1435 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Kimi K2.5 Instant leads
Grok-3 mini: 52.5 (#169), Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | Grok-3 mini | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1370 | 1420 |
| LMArena Creative Writing | 1342 | 1381 |
| LMArena Multi-Turn | 1355 | 1427 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini 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 Grok-3 mini or Kimi K2.5 Instant better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 40.8 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Kimi K2.5 Instant share?
16 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Kimi K2.5 Instant has 18.