# Inkling vs Llama 2-13B

> Inkling is the stronger model overall, scoring 44.1 to 29.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-vs-llama-2-13b
- Last updated: 2026-10-11
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Inkling scores higher in 8 categories and Llama 2-13B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling leads 65.2 to 29.8.
- The biggest single-benchmark swing is DTBench: 87.5% for Inkling and 42.2% for Llama 2-13B.

## Snapshot

| | Inkling | Llama 2-13B |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 44.1 | 29.6 |
| Rank | 80 | 309 |
| Context | 66K | — |
| Input $/M | $1.87 | — |
| Output $/M | $4.68 | — |
| Weights | Open | Open |

## Coding

- Inkling: 34.5 (#234)
- Llama 2-13B: 30.9 (#291)

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1464 | 1062 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |

## Agentic & Tool Use

- Inkling: 29.6 (#85)
- Llama 2-13B: —

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |

## Reasoning

- Inkling: 40.4 (#56)
- Llama 2-13B: 12.8 (#337)

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 21% | 0% |
| LMArena Hard Prompts | 1451 | 1051 |
| DTBench | 87.5% | 42.2% |
| Epoch Capabilities Index | 148.54 | 106.17 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| LMCA | 37.6% | — |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |

## Math

- Inkling: 31.3 (#225)
- Llama 2-13B: 31.1 (#229)

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| LMArena Math | 1479 | 1065 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| GSM8K | — | 36.9% |

## Knowledge

- Inkling: 55.1 (#49)
- Llama 2-13B: 28.1 (#249)

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1465 | 1030 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |

## Multimodal

- Inkling: —
- Llama 2-13B: —

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |

## Multilingual

- Inkling: 54.0 (#52)
- Llama 2-13B: 26.5 (#279)

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1434 | 1024 |
| LMArena Chinese | 1490 | 1001 |
| LMArena French | 1458 | 1044 |
| LMArena German | 1446 | 1009 |
| LMArena Japanese | 1429 | 894 |
| LMArena Korean | 1404 | 953 |
| LMArena Russian | 1429 | 1055 |
| LMArena Spanish | 1448 | 1087 |

## Instruction Following

- Inkling: 75.1 (#71)
- Llama 2-13B: 53.3 (#287)

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1045 |

## Long Context

- Inkling: 43.8 (#86)
- Llama 2-13B: 32.3 (#269)

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1434 | 1064 |

## Writing & Preference

- Inkling: 65.2 (#51)
- Llama 2-13B: 29.8 (#289)

| Benchmark | Inkling | Llama 2-13B |
|---|---|---|
| LMArena Text | 1441 | 1084 |
| LMArena Creative Writing | 1387 | 1047 |
| LMArena Multi-Turn | 1436 | 1050 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |

## FAQ

### Is Inkling better than Llama 2-13B?

Inkling is the stronger model overall, scoring 44.1 to 29.6 on the Noometry Index.

### Is Inkling or Llama 2-13B better for coding?

Inkling scores higher on coding benchmarks: 34.5 versus 30.9 in the Noometry coding category.

### How many benchmarks do Inkling and Llama 2-13B share?

20 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Llama 2-13B has 32.