Model comparison
Kimi K2.5 Instant vs Llama 4 Maverick
Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 30.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Kimi K2.5 Instant scores higher in 9 categories and Llama 4 Maverick in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.5 Instant leads 60.8 to 39.0.
Side by side
| Kimi K2.5 Instant | Llama 4 Maverick | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 42.9 | 30.6 |
| Released | — | 2025-04-05 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 18 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
Kimi K2.5 Instant: 42.3 (#95), Llama 4 Maverick: 26.3 (#318)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| LMArena Coding | 1483 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| LMArena WebDev | 1404 | — |
| SciCode | — | 33.1% |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Not comparable
Kimi K2.5 Instant: —, Llama 4 Maverick: 27.9 (#86)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning Kimi K2.5 Instant leads
Kimi K2.5 Instant: 28.5 (#88), Llama 4 Maverick: 10.1 (#337)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1281 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| Epoch Capabilities Index | — | 132.2 |
| ForecastBench | — | 57.5 |
Math Kimi K2.5 Instant leads
Kimi K2.5 Instant: 36.6 (#105), Llama 4 Maverick: 24.6 (#256)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| LMArena Math | 1443 | 1299 |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Kimi K2.5 Instant leads
Kimi K2.5 Instant: 39.5 (#121), Llama 4 Maverick: 33.3 (#196)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| LMArena Expert | 1438 | 1259 |
| GPQA Diamond | — | 67% |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
Multimodal Kimi K2.5 Instant leads
Kimi K2.5 Instant: 39.5 (#47), Llama 4 Maverick: 30.9 (#100)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1254 | 1141 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Kimi K2.5 Instant leads
Kimi K2.5 Instant: 52.2 (#89), Llama 4 Maverick: 42.4 (#190)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1406 | 1269 |
| LMArena Chinese | 1450 | 1277 |
| LMArena French | 1403 | 1258 |
| LMArena German | 1413 | 1291 |
| LMArena Korean | 1378 | 1203 |
| LMArena Russian | 1404 | 1286 |
| LMArena Spanish | 1448 | 1293 |
| LMArena Japanese | — | 1207 |
Instruction Following Kimi K2.5 Instant leads
Kimi K2.5 Instant: 75.5 (#61), Llama 4 Maverick: 71.9 (#140)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1430 | 1267 |
| IFEval | — | 90.8% |
Long Context Kimi K2.5 Instant leads
Kimi K2.5 Instant: 43.8 (#82), Llama 4 Maverick: 31.4 (#274)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1435 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Kimi K2.5 Instant leads
Kimi K2.5 Instant: 60.8 (#91), Llama 4 Maverick: 39.0 (#247)
| Benchmark | Kimi K2.5 Instant | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1420 | 1287 |
| LMArena Creative Writing | 1379 | 1266 |
| LMArena Multi-Turn | 1427 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
Frequently asked questions
Is Kimi K2.5 Instant better than Llama 4 Maverick?
Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 30.6 on the Noometry Index.
Is Kimi K2.5 Instant or Llama 4 Maverick better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.3 versus 26.3 in the Noometry coding category.
How many benchmarks do Kimi K2.5 Instant and Llama 4 Maverick share?
17 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and Llama 4 Maverick has 54.