Model comparison
Inkling vs Llama 3.2 3B
Inkling is the stronger model overall, scoring 44.1 to 28.9 on the Noometry Index. Llama 3.2 3B costs 21× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. Inkling scores higher in 8 categories and Llama 3.2 3B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling leads 65.2 to 24.7.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Llama 3.2 3B accepts more context: 131K tokens versus 66K.
Side by side
| Inkling | Llama 3.2 3B | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 44.1 | 28.9 |
| Released | 2026-07-15 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 66K | 131K |
| Max output | 66K | 118K |
| Input $ / M tokens | $1.87 | $0.05 |
| Output $ / M tokens | $4.68 | $0.33 |
| Results tracked | 41 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Inkling: 34.5 (#234), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Inkling | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1464 | 1098 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
| ALE-Bench | 946 | — |
Agentic & Tool Use Inkling leads
Inkling: 29.6 (#85), Llama 3.2 3B: 20.1 (#143)
| Benchmark | Inkling | Llama 3.2 3B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| Berkeley Function Calling Leaderboard | — | 21.9% |
| τ²-bench Banking | 25% | — |
| BALROG | — | 10.1% |
Reasoning Inkling leads
Inkling: 40.4 (#56), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Inkling | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1095 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.54 | — |
Math Llama 3.2 3B leads
Inkling: 31.3 (#225), Llama 3.2 3B: 32.4 (#214)
| Benchmark | Inkling | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1479 | 1126 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
Knowledge Inkling leads
Inkling: 55.1 (#49), Llama 3.2 3B: 29.7 (#235)
| Benchmark | Inkling | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1465 | 1090 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
Multilingual Inkling leads
Inkling: 54.0 (#52), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Inkling | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1434 | 1019 |
| LMArena Chinese | 1490 | 1017 |
| LMArena German | 1446 | 1056 |
| LMArena Russian | 1429 | 949 |
| LMArena French | 1458 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Inkling | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1089 |
Long Context Inkling leads
Inkling: 43.8 (#86), Llama 3.2 3B: 33.4 (#261)
| Benchmark | Inkling | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1434 | 1100 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Inkling | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1441 | 1110 |
| LMArena Creative Writing | 1387 | 1094 |
| EQ-Bench Creative Writing | 1611 | 595 |
| LMArena Multi-Turn | 1436 | 1105 |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Llama 3.2 3B?
Inkling is the stronger model overall, scoring 44.1 to 28.9 on the Noometry Index. Llama 3.2 3B costs 21× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling 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; Inkling lists at $1.87 and $4.68.
Is Inkling or Llama 3.2 3B better for coding?
Inkling scores higher on coding benchmarks: 34.5 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Llama 3.2 3B does, with 131K tokens against 66K.
How many benchmarks do Inkling and Llama 3.2 3B share?
14 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Llama 3.2 3B has 18.