Model comparison
Inkling vs Llama 2-7B
Inkling is the stronger model overall, scoring 44.1 to 28.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Inkling 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 leads 65.5 to 28.1.
- The biggest single-benchmark swing is Chess Puzzles: 21% for Inkling and 0% for Llama 2-7B.
Side by side
| Inkling | Llama 2-7B | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 44.1 | 28.6 |
| Released | 2026-07-15 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 66K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.87 | — |
| Output $ / M tokens | $4.68 | — |
| Results tracked | 41 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Inkling: 34.1 (#229), Llama 2-7B: 28.7 (#302)
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| LMArena Coding | 1463 | 1002 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.5 (#76), Llama 2-7B: —
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.6 (#48), Llama 2-7B: 15.1 (#309)
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| Chess Puzzles | 21% | 0% |
| LMArena Hard Prompts | 1452 | 1009 |
| Epoch Capabilities Index | 148.6 | 98.54 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| BIG-Bench Hard | — | 39.2% |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |
Math Inkling leads
Inkling: 31.2 (#198), Llama 2-7B: 28.2 (#231)
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| LMArena Math | 1482 | 1042 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| GSM8K | — | 16.7% |
Knowledge Inkling leads
Inkling: 55.2 (#44), Llama 2-7B: 27.7 (#243)
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| LMArena Expert | 1468 | 1036 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| ARC (AI2) Challenge | — | 45.9% |
| BoolQ | — | 77.9% |
| MMLU | — | 45.8% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
Inkling: —, Llama 2-7B: —
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |
Multilingual Inkling leads
Inkling: 54.2 (#49), Llama 2-7B: 23.9 (#288)
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1434 | 973 |
| LMArena Chinese | 1495 | 973 |
| LMArena French | 1453 | 969 |
| LMArena German | 1456 | 978 |
| LMArena Russian | 1430 | 995 |
| LMArena Spanish | 1442 | 1007 |
| LMArena Japanese | 1428 | — |
| LMArena Korean | 1401 | — |
Instruction Following Inkling leads
Inkling: 75.3 (#65), Llama 2-7B: 51.0 (#293)
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1427 | 1006 |
Long Context Inkling leads
Inkling: 43.9 (#79), Llama 2-7B: 30.4 (#282)
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | 1436 | 999 |
Writing & Preference Inkling leads
Inkling: 65.5 (#48), Llama 2-7B: 28.1 (#293)
| Benchmark | Inkling | Llama 2-7B |
|---|---|---|
| LMArena Text | 1443 | 1053 |
| LMArena Creative Writing | 1390 | 1033 |
| LMArena Multi-Turn | 1436 | 1029 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Llama 2-7B?
Inkling is the stronger model overall, scoring 44.1 to 28.6 on the Noometry Index.
Is Inkling or Llama 2-7B better for coding?
Inkling scores higher on coding benchmarks: 34.1 versus 28.7 in the Noometry coding category.
How many benchmarks do Inkling and Llama 2-7B share?
17 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Llama 2-7B has 29.