Model comparison
Kimi K2 (Jul 2025) vs Llama 3-70B
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 28.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 9 categories and Llama 3-70B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 40.1 to 12.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 64.4% for Kimi K2 (Jul 2025) and 35.1% for Llama 3-70B.
Side by side
| Kimi K2 (Jul 2025) | Llama 3-70B | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 40.9 | 28.5 |
| Released | 2025-07-12 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.57 | — |
| Output $ / M tokens | $2.30 | — |
| Results tracked | 42 | 31 |
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 3-70B: 35.3 (#215)
| Benchmark | Kimi K2 (Jul 2025) | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1399 | 1206 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| ALE-Bench | 597.5 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 32.2 (#59), Llama 3-70B: 20.9 (#132)
| Benchmark | Kimi K2 (Jul 2025) | Llama 3-70B |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| Cybench | — | 5% |
| METR Time Horizons | 59.2% | — |
Reasoning Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 22.7 (#173), Llama 3-70B: 17.4 (#284)
| Benchmark | Kimi K2 (Jul 2025) | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 64.4% | 35.1% |
| LMArena Hard Prompts | 1384 | 1195 |
| Epoch Capabilities Index | 146.02 | 122.91 |
| ForecastBench | 60.2 | 57.1 |
| SimpleBench | 26.3% | — |
| DTBench | — | 54.2% |
| WinoGrande | — | 83.5% |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 40.1 (#81), Llama 3-70B: 12.0 (#299)
| Benchmark | Kimi K2 (Jul 2025) | Llama 3-70B |
|---|---|---|
| LMArena Math | 1396 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| Omni-MATH | 65.4% | — |
| MATH Level 5 | — | 22.6% |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 36.9 (#153), Llama 3-70B: 20.8 (#272)
| Benchmark | Kimi K2 (Jul 2025) | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1363 | 1149 |
| GPQA Diamond | — | 40.6% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
| MMLU | — | 79.3% |
Multilingual Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 49.8 (#125), Llama 3-70B: 33.8 (#246)
| Benchmark | Kimi K2 (Jul 2025) | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1372 | 1142 |
| LMArena Chinese | 1416 | 1114 |
| LMArena French | 1379 | 1231 |
| LMArena German | 1386 | 1169 |
| LMArena Japanese | 1349 | 1017 |
| LMArena Korean | 1324 | 1017 |
| LMArena Russian | 1384 | 1159 |
| LMArena Spanish | 1383 | 1241 |
Instruction Following Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 71.3 (#151), Llama 3-70B: 62.8 (#233)
| Benchmark | Kimi K2 (Jul 2025) | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1347 | 1194 |
| IFEval | 85% | — |
Long Context Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 41.2 (#140), Llama 3-70B: 35.6 (#235)
| Benchmark | Kimi K2 (Jul 2025) | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1353 | 1174 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.5 (#76), Llama 3-70B: 43.0 (#225)
| Benchmark | Kimi K2 (Jul 2025) | Llama 3-70B |
|---|---|---|
| LMArena Text | 1380 | 1221 |
| LMArena Creative Writing | 1349 | 1210 |
| LMArena Multi-Turn | 1371 | 1223 |
| 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 3-70B?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 28.5 on the Noometry Index.
Is Kimi K2 (Jul 2025) or Llama 3-70B better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 35.3 in the Noometry coding category.
How many benchmarks do Kimi K2 (Jul 2025) and Llama 3-70B share?
20 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Llama 3-70B has 31.