Model comparison
Inkling-Small vs Llama 2-7B
Inkling-Small is the stronger model overall, scoring 46.5 to 28.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Llama 2-7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling-Small leads 59.8 to 28.1.
- The biggest single-benchmark swing is Chess Puzzles: 18% for Inkling-Small and 0% for Llama 2-7B.
Side by side
| Inkling-Small | Llama 2-7B | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 46.5 | 28.6 |
| 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 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.3 (#80), Llama 2-7B: 28.7 (#302)
| Benchmark | Inkling-Small | Llama 2-7B |
|---|---|---|
| LMArena Coding | 1451 | 1002 |
| LMArena WebDev | 1408 | — |
| SciCode | 48.7% | — |
Reasoning Inkling-Small leads
Inkling-Small: 39.0 (#53), Llama 2-7B: 15.1 (#309)
| Benchmark | Inkling-Small | Llama 2-7B |
|---|---|---|
| Chess Puzzles | 18% | 0% |
| LMArena Hard Prompts | 1424 | 1009 |
| Epoch Capabilities Index | 150.13 | 98.54 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Mystery Game Puzzles | 6% | — |
| BIG-Bench Hard | — | 39.2% |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |
Math Inkling-Small leads
Inkling-Small: 44.9 (#65), Llama 2-7B: 28.2 (#231)
| Benchmark | Inkling-Small | Llama 2-7B |
|---|---|---|
| LMArena Math | 1453 | 1042 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| GSM8K | — | 16.7% |
Knowledge Inkling-Small leads
Inkling-Small: 48.3 (#71), Llama 2-7B: 27.7 (#243)
| Benchmark | Inkling-Small | Llama 2-7B |
|---|---|---|
| LMArena Expert | 1442 | 1036 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| ARC (AI2) Challenge | — | 45.9% |
| BoolQ | — | 77.9% |
| MMLU | — | 45.8% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
Inkling-Small: 38.4 (#59), Llama 2-7B: —
| Benchmark | Inkling-Small | Llama 2-7B |
|---|---|---|
| LMArena Vision | 1235 | — |
| ScienceQA | — | 43.1% |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#102), Llama 2-7B: 23.9 (#288)
| Benchmark | Inkling-Small | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1400 | 973 |
| LMArena Chinese | 1458 | 973 |
| LMArena French | 1438 | 969 |
| LMArena German | 1412 | 978 |
| LMArena Russian | 1392 | 995 |
| LMArena Spanish | 1426 | 1007 |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1355 | — |
Instruction Following Inkling-Small leads
Inkling-Small: 73.9 (#112), Llama 2-7B: 51.0 (#293)
| Benchmark | Inkling-Small | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1397 | 1006 |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#113), Llama 2-7B: 30.4 (#282)
| Benchmark | Inkling-Small | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | 1401 | 999 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.8 (#102), Llama 2-7B: 28.1 (#293)
| Benchmark | Inkling-Small | Llama 2-7B |
|---|---|---|
| LMArena Text | 1413 | 1053 |
| LMArena Creative Writing | 1330 | 1033 |
| LMArena Multi-Turn | 1420 | 1029 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Llama 2-7B?
Inkling-Small is the stronger model overall, scoring 46.5 to 28.6 on the Noometry Index.
Is Inkling-Small or Llama 2-7B better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 28.7 in the Noometry coding category.
How many benchmarks do Inkling-Small and Llama 2-7B share?
17 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Llama 2-7B has 29.