# Inkling vs Llama-3.3-70B-Instruct

> Inkling is the stronger model overall, scoring 44.1 to 30.3 on the Noometry Index. Llama-3.3-70B-Instruct costs 17× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/inkling-vs-llama-3-3-70b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Inkling scores higher in 9 categories and Llama-3.3-70B-Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 13.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 5.1% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Llama-3.3-70B-Instruct accepts more context: 128K tokens versus 66K.

## Snapshot

| | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 44.1 | 30.3 |
| Rank | 75 | 283 |
| Context | 66K | 128K |
| Input $/M | $1.87 | $0.10 |
| Output $/M | $4.68 | $0.32 |
| Weights | Open | Open |

## Coding

- Inkling: 34.1 (#229)
- Llama-3.3-70B-Instruct: 30.6 (#284)

| Benchmark | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| SciCode | 47% | 26% |
| WeirdML | 32.3% | 14.4% |
| LMArena Coding | 1463 | 1268 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| BigCodeBench Instruct | — | 46.9% |
| LiveBench Coding | — | 36.6% |
| BigCodeBench Complete | — | 57.5% |
| ALE-Bench | 946 | — |

## Agentic & Tool Use

- Inkling: 29.5 (#76)
- Llama-3.3-70B-Instruct: 25.6 (#100)

| Benchmark | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| APEX-Agents | 33.8% | — |
| Berkeley Function Calling Leaderboard | — | 31.9% |
| τ²-bench Banking | 25% | — |
| BALROG | — | 23% |

## Reasoning

- Inkling: 40.6 (#48)
- Llama-3.3-70B-Instruct: 13.7 (#325)

| Benchmark | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| SimpleBench | 50% | 19.9% |
| CritPt | 5.4% | 0% |
| LMArena Hard Prompts | 1452 | 1257 |
| DTBench | 87.5% | 59.5% |
| LMCA | 37.6% | 17.5% |
| Epoch Capabilities Index | 148.6 | 127.32 |
| ARC-AGI-2 | 36.5% | — |
| ARC-AGI-1 | 79.5% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 50.8% |
| LiveBench Data Analysis | — | 49.5% |
| ForecastBench | — | 58.6 |
| LiveBench | — | 50.2% |

## Math

- Inkling: 31.2 (#198)
- Llama-3.3-70B-Instruct: 14.3 (#292)

| Benchmark | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 5.1% |
| LMArena Math | 1482 | 1268 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| LiveBench Math | — | 42.2% |
| MATH Level 5 | — | 41.6% |

## Knowledge

- Inkling: 55.2 (#44)
- Llama-3.3-70B-Instruct: 30.5 (#220)

| Benchmark | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | 88.3% | 47.4% |
| LMArena Expert | 1468 | 1225 |
| SimpleQA Verified | 40.3% | — |
| Confabulations | — | 22.8% |
| Vectara Hallucination Rate | — | 4.1% |
| MMLU | — | 86.3% |

## Multilingual

- Inkling: 54.2 (#49)
- Llama-3.3-70B-Instruct: 40.1 (#215)

| Benchmark | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1434 | 1236 |
| LMArena Chinese | 1495 | 1217 |
| LMArena French | 1453 | 1280 |
| LMArena German | 1456 | 1251 |
| LMArena Japanese | 1428 | 1149 |
| LMArena Korean | 1401 | 1142 |
| LMArena Russian | 1430 | 1252 |
| LMArena Spanish | 1442 | 1269 |

## Instruction Following

- Inkling: 75.3 (#65)
- Llama-3.3-70B-Instruct: 71.3 (#152)

| Benchmark | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Instruction Following | 1427 | 1242 |
| LiveBench Instruction Following | — | 82.7% |

## Long Context

- Inkling: 43.9 (#79)
- Llama-3.3-70B-Instruct: 26.4 (#290)

| Benchmark | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1436 | 1256 |
| Fiction.LiveBench | — | 33.3% |

## Writing & Preference

- Inkling: 65.5 (#48)
- Llama-3.3-70B-Instruct: 47.8 (#203)

| Benchmark | Inkling | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1443 | 1274 |
| LMArena Creative Writing | 1390 | 1250 |
| LMArena Multi-Turn | 1436 | 1279 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LiveBench Language | — | 39.2% |

## FAQ

### Is Inkling better than Llama-3.3-70B-Instruct?

Inkling is the stronger model overall, scoring 44.1 to 30.3 on the Noometry Index. Llama-3.3-70B-Instruct costs 17× 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-3.3-70B-Instruct?

Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Inkling lists at $1.87 and $4.68.

### Is Inkling or Llama-3.3-70B-Instruct better for coding?

Inkling scores higher on coding benchmarks: 34.1 versus 30.6 in the Noometry coding category.

### Which has the bigger context window?

Llama-3.3-70B-Instruct does, with 128K tokens against 66K.

### How many benchmarks do Inkling and Llama-3.3-70B-Instruct share?

26 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Llama-3.3-70B-Instruct has 43.