Model comparison
Kimi K2.7 Code vs Llama 3.2 90B
Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 27.1 on the Noometry Index.
Last verified . 3 shared benchmarks.
MetaSummary
- They share 3 benchmarks with published results for both. Kimi K2.7 Code scores higher in 3 categories and Llama 3.2 90B in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.7 Code leads 52.6 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Kimi K2.7 Code and 2.6% for Llama 3.2 90B.
Side by side
| Kimi K2.7 Code | Llama 3.2 90B | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 43.0 | 27.1 |
| Released | 2026-06-12 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.95 | — |
| Output $ / M tokens | $4 | — |
| Results tracked | 19 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Kimi K2.7 Code: 42.4 (#92), Llama 3.2 90B: —
| Benchmark | Kimi K2.7 Code | Llama 3.2 90B |
|---|---|---|
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena WebDev | 1473 | — |
| SciCode | 47.5% | — |
| WeirdML | 54.1% | — |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Llama 3.2 90B leads
Kimi K2.7 Code: 23.9 (#115), Llama 3.2 90B: 29.7 (#73)
| Benchmark | Kimi K2.7 Code | Llama 3.2 90B |
|---|---|---|
| APEX-Agents | 37.6% | — |
| BALROG | — | 27.3% |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 38.2 (#56), Llama 3.2 90B: 20.9 (#207)
| Benchmark | Kimi K2.7 Code | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 150.01 | 125.5 |
| SimpleBench | 57.9% | — |
| CritPt | 10% | — |
| Chess Puzzles | 21% | — |
| EnigmaEval | — | 0.4% |
| Surface Evolver Bench | 48.8% | — |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.6 (#39), Llama 3.2 90B: 10.4 (#302)
| Benchmark | Kimi K2.7 Code | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 2.6% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| MATH Level 5 | — | 39.4% |
Knowledge Kimi K2.7 Code leads
Kimi K2.7 Code: 53.6 (#51), Llama 3.2 90B: 21.7 (#269)
| Benchmark | Kimi K2.7 Code | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 87.9% | 41% |
| SimpleQA Verified | 36.5% | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
Kimi K2.7 Code: —, Llama 3.2 90B: 24.9 (#119)
| Benchmark | Kimi K2.7 Code | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Frequently asked questions
Is Kimi K2.7 Code better than Llama 3.2 90B?
Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 27.1 on the Noometry Index.
How many benchmarks do Kimi K2.7 Code and Llama 3.2 90B share?
3 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Llama 3.2 90B has 9.