Model comparison
Inkling vs Llama 3.2 90B
Inkling is the stronger model overall, scoring 44.1 to 27.5 on the Noometry Index.
Last verified . 3 shared benchmarks.
MetaSummary
- They share 3 benchmarks with published results for both. Inkling scores higher in 3 categories and Llama 3.2 90B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 21.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 2.6% for Llama 3.2 90B.
Side by side
| Inkling | Llama 3.2 90B | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 44.1 | 27.5 |
| Released | 2026-07-15 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 66K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.87 | — |
| Output $ / M tokens | $4.68 | — |
| Results tracked | 41 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Inkling: 34.5 (#234), Llama 3.2 90B: —
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| LMArena Coding | 1464 | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Too close to call
Inkling: 29.6 (#85), Llama 3.2 90B: 30.0 (#80)
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
| BALROG | — | 27.3% |
Reasoning Inkling leads
Inkling: 40.4 (#56), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 148.54 | 125.5 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1451 | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
Math Inkling leads
Inkling: 31.3 (#225), Llama 3.2 90B: 11.1 (#308)
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 2.6% |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| LMArena Math | 1479 | — |
| MATH Level 5 | — | 39.4% |
Knowledge Inkling leads
Inkling: 55.1 (#49), Llama 3.2 90B: 21.7 (#274)
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 88.3% | 41% |
| SimpleQA Verified | 40.3% | — |
| LMArena Expert | 1465 | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
Inkling: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
Inkling: 54.0 (#52), Llama 3.2 90B: —
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1434 | — |
| LMArena Chinese | 1490 | — |
| LMArena French | 1458 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
| LMArena Russian | 1429 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Not comparable
Inkling: 75.1 (#71), Llama 3.2 90B: —
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1426 | — |
Long Context Not comparable
Inkling: 43.8 (#86), Llama 3.2 90B: —
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1434 | — |
Writing & Preference Not comparable
Inkling: 65.2 (#51), Llama 3.2 90B: —
| Benchmark | Inkling | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1441 | — |
| LMArena Creative Writing | 1387 | — |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LMArena Multi-Turn | 1436 | — |
Frequently asked questions
Is Inkling better than Llama 3.2 90B?
Inkling is the stronger model overall, scoring 44.1 to 27.5 on the Noometry Index.
How many benchmarks do Inkling and Llama 3.2 90B share?
3 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Llama 3.2 90B has 9.