Model comparison
Kimi K3 vs Llama 4 Scout
Kimi K3 is the stronger model overall, scoring 59.5 to 27.7 on the Noometry Index. Llama 4 Scout costs 40× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
MetaSummary
- They share 28 benchmarks with published results for both. Kimi K3 scores higher in 10 categories and Llama 4 Scout in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 19.6.
- The biggest single-benchmark swing is ARC-AGI-1: 94.5% for Kimi K3 and 0.5% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 128K.
Side by side
| Kimi K3 | Llama 4 Scout | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 59.5 | 27.7 |
| Released | 2026-07-16 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 1.05M | 128K |
| Max output | 1.05M | 4K |
| Input $ / M tokens | $3 | $0.10 |
| Output $ / M tokens | $15 | $0.30 |
| Results tracked | 53 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Llama 4 Scout: 20.2 (#339)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| SciCode | 59.5% | 17% |
| LMArena Coding | 1508 | 1286 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| SWE-bench Verified (bash only) | — | 9.1% |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| WeirdML | 82.6% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Kimi K3 leads
Kimi K3: 41.8 (#20), Llama 4 Scout: 24.6 (#119)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| APEX-Agents | 50.6% | — |
| Berkeley Function Calling Leaderboard | — | 28.1% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Llama 4 Scout: 9.1 (#345)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 60.4% | 0% |
| ARC-AGI-1 | 94.5% | 0.5% |
| CritPt | 23.4% | 0% |
| LMArena Hard Prompts | 1496 | 1266 |
| DTBench | 91.2% | 57.9% |
| LMCA | 52.7% | 12% |
| Epoch Capabilities Index | 157.45 | 129.64 |
| ForecastBench | 61.1 | 57.5 |
| SimpleBench | 60.7% | — |
| Kagi LLM Benchmark | — | 36.9% |
| NYT Connections (extended) | 93.6% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| Surface Evolver Bench | 95% | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Llama 4 Scout: 19.6 (#286)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 7.8% |
| LMArena Math | 1491 | 1287 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| ProofBench | 87% | — |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Llama 4 Scout: 31.9 (#217)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 93.1% | 51.8% |
| LMArena Expert | 1521 | 1235 |
| SimpleQA Verified | 50.6% | — |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
Multimodal Kimi K3 leads
Kimi K3: 37.8 (#70), Llama 4 Scout: 32.2 (#102)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Llama 4 Scout: 41.0 (#212)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1466 | 1252 |
| LMArena Chinese | 1529 | 1255 |
| LMArena French | 1491 | 1282 |
| LMArena German | 1488 | 1272 |
| LMArena Japanese | 1487 | 1206 |
| LMArena Korean | 1458 | 1207 |
| LMArena Russian | 1482 | 1263 |
| LMArena Spanish | 1472 | 1278 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Llama 4 Scout: 65.8 (#217)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1483 | 1248 |
| IFEval | — | 81.8% |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Llama 4 Scout: 27.5 (#294)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1494 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Llama 4 Scout: 37.0 (#261)
| Benchmark | Kimi K3 | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1476 | 1279 |
| LMArena Creative Writing | 1454 | 1249 |
| EQ-Bench Creative Writing | 2082 | 783 |
| LMArena Multi-Turn | 1488 | 1280 |
| WildBench | — | 78% |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Llama 4 Scout?
Kimi K3 is the stronger model overall, scoring 59.5 to 27.7 on the Noometry Index. Llama 4 Scout costs 40× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or Llama 4 Scout?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Llama 4 Scout better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 128K.
How many benchmarks do Kimi K3 and Llama 4 Scout share?
28 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Llama 4 Scout has 43.