Model comparison
Kimi K3 vs Llama 3.2 3B
Kimi K3 is the stronger model overall, scoring 59.5 to 28.9 on the Noometry Index. Llama 3.2 3B costs 50× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. Kimi K3 scores higher in 9 categories and Llama 3.2 3B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K3 leads 76.6 to 24.7.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 131K.
Side by side
| Kimi K3 | Llama 3.2 3B | |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 59.5 | 28.9 |
| Released | 2026-07-16 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 1.05M | 131K |
| Max output | 1.05M | 118K |
| Input $ / M tokens | $3 | $0.05 |
| Output $ / M tokens | $15 | $0.33 |
| Results tracked | 53 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1508 | 1098 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Kimi K3 leads
Kimi K3: 41.8 (#20), Llama 3.2 3B: 20.1 (#143)
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| APEX-Agents | 50.6% | — |
| Berkeley Function Calling Leaderboard | — | 21.9% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| BALROG | — | 10.1% |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1496 | 1095 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| Epoch Capabilities Index | 157.45 | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Llama 3.2 3B: 32.4 (#214)
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1491 | 1126 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| ProofBench | 87% | — |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Llama 3.2 3B: 29.7 (#235)
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1521 | 1090 |
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Llama 3.2 3B: —
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1466 | 1019 |
| LMArena Chinese | 1529 | 1017 |
| LMArena German | 1488 | 1056 |
| LMArena Russian | 1482 | 949 |
| LMArena French | 1491 | — |
| LMArena Japanese | 1487 | — |
| LMArena Korean | 1458 | — |
| LMArena Spanish | 1472 | — |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1483 | 1089 |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Llama 3.2 3B: 33.4 (#261)
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1494 | 1100 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Kimi K3 | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1476 | 1110 |
| LMArena Creative Writing | 1454 | 1094 |
| EQ-Bench Creative Writing | 2082 | 595 |
| LMArena Multi-Turn | 1488 | 1105 |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Llama 3.2 3B?
Kimi K3 is the stronger model overall, scoring 59.5 to 28.9 on the Noometry Index. Llama 3.2 3B costs 50× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or Llama 3.2 3B?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Llama 3.2 3B better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 131K.
How many benchmarks do Kimi K3 and Llama 3.2 3B share?
14 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Llama 3.2 3B has 18.