Model comparison
Kimi K2.7 Code vs Llama 3.1 Tulu 3 8b
Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 35.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- The widest gap is in math, where Kimi K2.7 Code leads 52.6 to 31.3.
Side by side
| Kimi K2.7 Code | Llama 3.1 Tulu 3 8b | |
|---|---|---|
| Provider | Moonshot AI | Allen Institute for AI (Ai2) |
| Noometry Index | 43.0 | 35.1 |
| Released | 2026-06-12 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.95 | — |
| Output $ / M tokens | $4 | — |
| Results tracked | 19 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
Kimi K2.7 Code: 42.4 (#92), Llama 3.1 Tulu 3 8b: 33.9 (#235)
| Benchmark | Kimi K2.7 Code | Llama 3.1 Tulu 3 8b |
|---|---|---|
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena WebDev | 1473 | — |
| SciCode | 47.5% | — |
| WeirdML | 54.1% | — |
| LMArena Coding | — | 1184 |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Not comparable
Kimi K2.7 Code: 23.9 (#115), Llama 3.1 Tulu 3 8b: —
| Benchmark | Kimi K2.7 Code | Llama 3.1 Tulu 3 8b |
|---|---|---|
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 38.2 (#56), Llama 3.1 Tulu 3 8b: 21.8 (#188)
| Benchmark | Kimi K2.7 Code | Llama 3.1 Tulu 3 8b |
|---|---|---|
| SimpleBench | 57.9% | — |
| CritPt | 10% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | — | 1174 |
| Surface Evolver Bench | 48.8% | — |
| Epoch Capabilities Index | 150.01 | — |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.6 (#39), Llama 3.1 Tulu 3 8b: 31.3 (#196)
| Benchmark | Kimi K2.7 Code | Llama 3.1 Tulu 3 8b |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| LMArena Math | — | 1195 |
Knowledge Not comparable
Kimi K2.7 Code: 53.6 (#51), Llama 3.1 Tulu 3 8b: —
| Benchmark | Kimi K2.7 Code | Llama 3.1 Tulu 3 8b |
|---|---|---|
| GPQA Diamond | 87.9% | — |
| SimpleQA Verified | 36.5% | — |
Multilingual Not comparable
Kimi K2.7 Code: —, Llama 3.1 Tulu 3 8b: 35.6 (#241)
| Benchmark | Kimi K2.7 Code | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Non-English | — | 1169 |
| LMArena Chinese | — | 1175 |
| LMArena Russian | — | 1193 |
Instruction Following Not comparable
Kimi K2.7 Code: —, Llama 3.1 Tulu 3 8b: 61.6 (#241)
| Benchmark | Kimi K2.7 Code | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Instruction Following | — | 1174 |
Long Context Not comparable
Kimi K2.7 Code: —, Llama 3.1 Tulu 3 8b: 35.8 (#234)
| Benchmark | Kimi K2.7 Code | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Longer Query | — | 1181 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, Llama 3.1 Tulu 3 8b: 39.9 (#240)
| Benchmark | Kimi K2.7 Code | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Text | — | 1193 |
| LMArena Creative Writing | — | 1182 |
| LMArena Multi-Turn | — | 1154 |
Frequently asked questions
Is Kimi K2.7 Code better than Llama 3.1 Tulu 3 8b?
Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 35.1 on the Noometry Index.
Is Kimi K2.7 Code or Llama 3.1 Tulu 3 8b better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 33.9 in the Noometry coding category.
How many benchmarks do Kimi K2.7 Code and Llama 3.1 Tulu 3 8b share?
0 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Llama 3.1 Tulu 3 8b has 11.