Model comparison
Kimi K2.5 vs Llama 2-13B
Kimi K2.5 is the stronger model overall, scoring 48.1 to 29.6 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.5 leads 65.1 to 29.8.
- The biggest single-benchmark swing is Chess Puzzles: 12% for Kimi K2.5 and 0% for Llama 2-13B.
Side by side
| Kimi K2.5 | Llama 2-13B | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 48.1 | 29.6 |
| Released | 2026-01-27 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.45 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 51 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Kimi K2.5: 48.8 (#53), Llama 2-13B: 30.9 (#291)
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1474 | 1062 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| LMArena WebDev | 1437 | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| WeirdML | 45.6% | — |
| ALE-Bench | 821.65 | — |
Agentic & Tool Use Not comparable
Kimi K2.5: 34.2 (#48), Llama 2-13B: —
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#80), Llama 2-13B: 12.8 (#337)
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 12% | 0% |
| LMArena Hard Prompts | 1453 | 1051 |
| Epoch Capabilities Index | 148.03 | 106.17 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 78.5% | — |
| NYT Connections (extended) | 69.9% | — |
| ARC-AGI-1 | 65.3% | — |
| CritPt | 3.1% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Kimi K2.5 leads
Kimi K2.5: 51.8 (#53), Llama 2-13B: 31.1 (#229)
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1470 | 1065 |
| MathArena Final-Answer Competitions | 62.3% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 36.9% |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#56), Llama 2-13B: 28.1 (#249)
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1466 | 1030 |
| GPQA Diamond | 87.6% | — |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| Vectara Hallucination Rate | 14.2% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Llama 2-13B: —
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
| ScienceQA | — | 55.8% |
Multilingual Kimi K2.5 leads
Kimi K2.5: 53.9 (#53), Llama 2-13B: 26.5 (#279)
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1433 | 1024 |
| LMArena Chinese | 1495 | 1001 |
| LMArena French | 1454 | 1044 |
| LMArena German | 1441 | 1009 |
| LMArena Japanese | 1421 | 894 |
| LMArena Korean | 1410 | 953 |
| LMArena Russian | 1435 | 1055 |
| LMArena Spanish | 1450 | 1087 |
Instruction Following Kimi K2.5 leads
Kimi K2.5: 75.3 (#64), Llama 2-13B: 53.3 (#287)
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1431 | 1045 |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Llama 2-13B: 32.3 (#269)
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1445 | 1064 |
| Fiction.LiveBench | 86.1% | — |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |
Writing & Preference Kimi K2.5 leads
Kimi K2.5: 65.1 (#53), Llama 2-13B: 29.8 (#289)
| Benchmark | Kimi K2.5 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1445 | 1084 |
| LMArena Creative Writing | 1423 | 1047 |
| LMArena Multi-Turn | 1444 | 1050 |
| EQ-Bench Creative Writing | 1579 | — |
Frequently asked questions
Is Kimi K2.5 better than Llama 2-13B?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 29.6 on the Noometry Index.
Is Kimi K2.5 or Llama 2-13B better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 30.9 in the Noometry coding category.
How many benchmarks do Kimi K2.5 and Llama 2-13B share?
19 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Llama 2-13B has 32.