Model comparison
DeepSeek LLM 67B vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 24.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Kimi K3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 8.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 97.2% for Kimi K3.
Side by side
| DeepSeek LLM 67B | Kimi K3 | |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 24.9 | 59.5 |
| Released | 2023-11-29 | 2026-07-16 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 1.05M |
| Input $ / M tokens | — | $3 |
| Output $ / M tokens | — | $15 |
| Results tracked | 15 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
DeepSeek LLM 67B: 31.9 (#278), Kimi K3: 61.0 (#10)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| LMArena Coding | 1096 | 1508 |
| 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
DeepSeek LLM 67B: —, Kimi K3: 41.8 (#20)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| 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
DeepSeek LLM 67B: 16.5 (#304), Kimi K3: 63.0 (#17)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| Chess Puzzles | 0% | 39% |
| LMArena Hard Prompts | 1070 | 1496 |
| Epoch Capabilities Index | 110.5 | 157.45 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| ForecastBench | — | 61.1 |
Math Kimi K3 leads
DeepSeek LLM 67B: 8.7 (#324), Kimi K3: 74.2 (#16)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 97.2% |
| LMArena Math | 1108 | 1491 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| ProofBench | — | 87% |
| MATH Level 5 | 6.4% | — |
Knowledge Kimi K3 leads
DeepSeek LLM 67B: 7.0 (#313), Kimi K3: 63.2 (#21)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| GPQA Diamond | 24.6% | 93.1% |
| SimpleQA Verified | — | 50.6% |
| LMArena Expert | — | 1521 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Kimi K3: 37.8 (#70)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
DeepSeek LLM 67B: 29.4 (#267), Kimi K3: 56.3 (#21)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1073 | 1466 |
| LMArena Chinese | 1132 | 1529 |
| LMArena French | — | 1491 |
| LMArena German | — | 1488 |
| LMArena Japanese | — | 1487 |
| LMArena Korean | — | 1458 |
| LMArena Russian | — | 1482 |
| LMArena Spanish | — | 1472 |
Instruction Following Kimi K3 leads
DeepSeek LLM 67B: 55.4 (#277), Kimi K3: 77.7 (#14)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1483 |
Long Context Kimi K3 leads
DeepSeek LLM 67B: 33.1 (#265), Kimi K3: 45.8 (#29)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1092 | 1494 |
Writing & Preference Kimi K3 leads
DeepSeek LLM 67B: 31.6 (#282), Kimi K3: 76.6 (#4)
| Benchmark | DeepSeek LLM 67B | Kimi K3 |
|---|---|---|
| LMArena Text | 1105 | 1476 |
| LMArena Creative Writing | 1067 | 1454 |
| LMArena Multi-Turn | 1082 | 1488 |
| EQ-Bench Creative Writing | — | 2082 |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is DeepSeek LLM 67B better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Kimi K3 share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Kimi K3 has 53.