Model comparison
Kimi K2 (Jul 2025) vs Llama 2-7B
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 28.6 on the Noometry Index.
Last verified . 16 shared benchmarks.
MetaSummary
- They share 16 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 8 categories and Llama 2-7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.5 to 28.1.
Side by side
| Kimi K2 (Jul 2025) | Llama 2-7B | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 40.9 | 28.6 |
| Released | 2025-07-12 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.57 | — |
| Output $ / M tokens | $2.30 | — |
| Results tracked | 42 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 43.1 (#83), Llama 2-7B: 28.7 (#302)
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| LMArena Coding | 1399 | 1002 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.2 (#59), Llama 2-7B: —
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 22.7 (#173), Llama 2-7B: 15.1 (#309)
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1009 |
| Epoch Capabilities Index | 146.02 | 98.54 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| Chess Puzzles | — | 0% |
| BIG-Bench Hard | — | 39.2% |
| ForecastBench | 60.2 | — |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 40.1 (#81), Llama 2-7B: 28.2 (#231)
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| LMArena Math | 1396 | 1042 |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 16.7% |
Knowledge Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 36.9 (#153), Llama 2-7B: 27.7 (#243)
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| LMArena Expert | 1363 | 1036 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
| ARC (AI2) Challenge | — | 45.9% |
| BoolQ | — | 77.9% |
| MMLU | — | 45.8% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
Kimi K2 (Jul 2025): —, Llama 2-7B: —
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |
Multilingual Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 49.8 (#125), Llama 2-7B: 23.9 (#288)
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1372 | 973 |
| LMArena Chinese | 1416 | 973 |
| LMArena French | 1379 | 969 |
| LMArena German | 1386 | 978 |
| LMArena Russian | 1384 | 995 |
| LMArena Spanish | 1383 | 1007 |
| LMArena Japanese | 1349 | — |
| LMArena Korean | 1324 | — |
Instruction Following Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 71.3 (#151), Llama 2-7B: 51.0 (#293)
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1347 | 1006 |
| IFEval | 85% | — |
Long Context Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 41.2 (#140), Llama 2-7B: 30.4 (#282)
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | 1353 | 999 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.5 (#76), Llama 2-7B: 28.1 (#293)
| Benchmark | Kimi K2 (Jul 2025) | Llama 2-7B |
|---|---|---|
| LMArena Text | 1380 | 1053 |
| LMArena Creative Writing | 1349 | 1033 |
| LMArena Multi-Turn | 1371 | 1029 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Llama 2-7B?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 28.6 on the Noometry Index.
Is Kimi K2 (Jul 2025) or Llama 2-7B better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 28.7 in the Noometry coding category.
How many benchmarks do Kimi K2 (Jul 2025) and Llama 2-7B share?
16 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Llama 2-7B has 29.