Model comparison
Inkling-Small vs Llama 2-13B
Inkling-Small is the stronger model overall, scoring 46.5 to 29.6 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling-Small leads 59.6 to 29.8.
- The biggest single-benchmark swing is Chess Puzzles: 18% for Inkling-Small and 0% for Llama 2-13B.
Side by side
| Inkling-Small | Llama 2-13B | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 46.5 | 29.6 |
| Released | 2026-07-15 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 524K | — |
| Max output | 1.05M | — |
| Input $ / M tokens | $0.45 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Llama 2-13B: 30.9 (#291)
| Benchmark | Inkling-Small | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1451 | 1062 |
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Llama 2-13B: 12.8 (#337)
| Benchmark | Inkling-Small | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 18% | 0% |
| LMArena Hard Prompts | 1423 | 1051 |
| Epoch Capabilities Index | 150.15 | 106.17 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Llama 2-13B: 31.1 (#229)
| Benchmark | Inkling-Small | Llama 2-13B |
|---|---|---|
| LMArena Math | 1459 | 1065 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| GSM8K | — | 36.9% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Llama 2-13B: 28.1 (#249)
| Benchmark | Inkling-Small | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1442 | 1030 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Llama 2-13B: —
| Benchmark | Inkling-Small | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1235 | — |
| ScienceQA | — | 55.8% |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), Llama 2-13B: 26.5 (#279)
| Benchmark | Inkling-Small | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1402 | 1024 |
| LMArena Chinese | 1465 | 1001 |
| LMArena French | 1436 | 1044 |
| LMArena German | 1405 | 1009 |
| LMArena Japanese | 1405 | 894 |
| LMArena Korean | 1363 | 953 |
| LMArena Russian | 1391 | 1055 |
| LMArena Spanish | 1428 | 1087 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.8 (#114), Llama 2-13B: 53.3 (#287)
| Benchmark | Inkling-Small | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1399 | 1045 |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#118), Llama 2-13B: 32.3 (#269)
| Benchmark | Inkling-Small | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1401 | 1064 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), Llama 2-13B: 29.8 (#289)
| Benchmark | Inkling-Small | Llama 2-13B |
|---|---|---|
| LMArena Text | 1414 | 1084 |
| LMArena Creative Writing | 1331 | 1047 |
| LMArena Multi-Turn | 1418 | 1050 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Llama 2-13B?
Inkling-Small is the stronger model overall, scoring 46.5 to 29.6 on the Noometry Index.
Is Inkling-Small or Llama 2-13B better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 30.9 in the Noometry coding category.
How many benchmarks do Inkling-Small and Llama 2-13B share?
19 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Llama 2-13B has 32.