Model comparison
Kimi K2.5 Instant vs Llama 3.1-8B
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 23.0 on the Noometry Index.
Last verified . 16 shared benchmarks.
MetaSummary
- They share 16 benchmarks with published results for both. Kimi K2.5 Instant scores higher in 8 categories and Llama 3.1-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 Instant leads 40.2 to 8.0.
Side by side
| Kimi K2.5 Instant | Llama 3.1-8B | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 43.6 | 23.0 |
| Released | — | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 18 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
Kimi K2.5 Instant: 42.6 (#97), Llama 3.1-8B: 20.2 (#340)
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| LMArena Coding | 1484 | 1195 |
| LMArena WebDev | 1404 | — |
| SciCode | — | 13.2% |
| WeirdML | — | 1.7% |
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 40.5% |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |
Agentic & Tool Use Not comparable
Kimi K2.5 Instant: —, Llama 3.1-8B: 22.5 (#131)
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 25.8% |
| BALROG | — | 15.1% |
Reasoning Kimi K2.5 Instant leads
Kimi K2.5 Instant: 29.7 (#90), Llama 3.1-8B: 14.9 (#321)
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1175 |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 5.4% |
| Epoch Capabilities Index | — | 116.57 |
| PIQA | — | 81.2% |
Math Kimi K2.5 Instant leads
Kimi K2.5 Instant: 39.4 (#105), Llama 3.1-8B: 10.2 (#317)
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| LMArena Math | 1442 | 1179 |
| OTIS Mock AIME 2024-2025 | — | 1.7% |
| Omni-MATH | — | 13.7% |
| MATH Level 5 | — | 22.9% |
| GSM8K | — | 82.4% |
Knowledge Kimi K2.5 Instant leads
Kimi K2.5 Instant: 40.2 (#123), Llama 3.1-8B: 8.0 (#307)
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| LMArena Expert | 1440 | 1144 |
| GPQA Diamond | — | 27% |
| MMLU-Pro | — | 40.6% |
| GPQA (HELM) | — | 24.7% |
| BoolQ | — | 82.8% |
| MMLU | — | 56.1% |
Multimodal Not comparable
Kimi K2.5 Instant: 40.2 (#50), Llama 3.1-8B: —
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| LMArena Vision | 1254 | — |
Multilingual Kimi K2.5 Instant leads
Kimi K2.5 Instant: 52.0 (#94), Llama 3.1-8B: 34.0 (#249)
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1406 | 1148 |
| LMArena Chinese | 1449 | 1151 |
| LMArena French | 1403 | 1177 |
| LMArena German | 1413 | 1144 |
| LMArena Korean | 1378 | 1053 |
| LMArena Russian | 1404 | 1158 |
| LMArena Spanish | 1447 | 1169 |
| LMArena Japanese | — | 1061 |
Instruction Following Kimi K2.5 Instant leads
Kimi K2.5 Instant: 75.3 (#65), Llama 3.1-8B: 58.9 (#258)
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| LMArena Instruction Following | 1430 | 1159 |
| IFEval | — | 74.3% |
Long Context Kimi K2.5 Instant leads
Kimi K2.5 Instant: 43.9 (#83), Llama 3.1-8B: 35.8 (#238)
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1435 | 1182 |
Writing & Preference Kimi K2.5 Instant leads
Kimi K2.5 Instant: 60.6 (#95), Llama 3.1-8B: 29.7 (#290)
| Benchmark | Kimi K2.5 Instant | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1420 | 1187 |
| LMArena Creative Writing | 1381 | 1154 |
| LMArena Multi-Turn | 1427 | 1172 |
| EQ-Bench Creative Writing | — | 713 |
| WildBench | — | 68.7% |
Frequently asked questions
Is Kimi K2.5 Instant better than Llama 3.1-8B?
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 23.0 on the Noometry Index.
Is Kimi K2.5 Instant or Llama 3.1-8B better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 20.2 in the Noometry coding category.
How many benchmarks do Kimi K2.5 Instant and Llama 3.1-8B share?
16 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and Llama 3.1-8B has 43.