Model comparison
Kimi K3 vs Llama 13b
Kimi K3 is the stronger model overall, scoring 59.5 to 24.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
MetaSummary
- They share 9 benchmarks with published results for both. Kimi K3 scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K3 leads 76.6 to 13.8.
Side by side
| Kimi K3 | Llama 13b | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 59.5 | 24.4 |
| Released | 2026-07-16 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 1.05M | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 53 | 21 |
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 13b: 21.4 (#337)
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| LMArena Coding | 1508 | 683 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), Llama 13b: —
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| APEX-Agents | 50.6% | — |
| 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 13b: 14.0 (#329)
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1496 | 728 |
| Epoch Capabilities Index | 157.45 | 100.58 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| BIG-Bench Hard | — | 37.9% |
| ForecastBench | 61.1 | — |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Llama 13b: 26.7 (#256)
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| LMArena Math | 1491 | 838 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| ProofBench | 87% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Kimi K3: 63.2 (#21), Llama 13b: —
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |
| LMArena Expert | 1521 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Llama 13b: —
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
| ScienceQA | — | 43.3% |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Llama 13b: 16.6 (#297)
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| LMArena Non-English | 1466 | 819 |
| LMArena Chinese | 1529 | — |
| LMArena French | 1491 | — |
| LMArena German | 1488 | — |
| LMArena Japanese | 1487 | — |
| LMArena Korean | 1458 | — |
| LMArena Russian | 1482 | — |
| LMArena Spanish | 1472 | — |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Llama 13b: 36.7 (#305)
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1483 | 781 |
Long Context Not comparable
Kimi K3: 45.8 (#29), Llama 13b: —
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1494 | — |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Llama 13b: 13.8 (#312)
| Benchmark | Kimi K3 | Llama 13b |
|---|---|---|
| LMArena Text | 1476 | 834 |
| LMArena Creative Writing | 1454 | 794 |
| LMArena Multi-Turn | 1488 | 753 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Llama 13b?
Kimi K3 is the stronger model overall, scoring 59.5 to 24.4 on the Noometry Index.
Is Kimi K3 or Llama 13b better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 21.4 in the Noometry coding category.
How many benchmarks do Kimi K3 and Llama 13b share?
9 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Llama 13b has 21.