Model comparison
Inkling vs Llama 3.1-8B
Inkling is the stronger model overall, scoring 44.1 to 23.0 on the Noometry Index. Llama 3.1-8B costs 45× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
MetaSummary
- They share 27 benchmarks with published results for both. Inkling scores higher in 9 categories and Llama 3.1-8B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 8.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 1.7% for Llama 3.1-8B.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Llama 3.1-8B accepts more context: 128K tokens versus 66K.
Side by side
| Inkling | Llama 3.1-8B | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 44.1 | 23.0 |
| Released | 2026-07-15 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 66K | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $1.87 | $0.05 |
| Output $ / M tokens | $4.68 | $0.08 |
| Results tracked | 41 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Inkling: 34.5 (#234), Llama 3.1-8B: 20.2 (#340)
| Benchmark | Inkling | Llama 3.1-8B |
|---|---|---|
| SciCode | 47% | 13.2% |
| WeirdML | 32.3% | 1.7% |
| LMArena Coding | 1464 | 1195 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 40.5% |
| ALE-Bench | 946 | — |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |
Agentic & Tool Use Inkling leads
Inkling: 29.6 (#85), Llama 3.1-8B: 22.5 (#131)
| Benchmark | Inkling | Llama 3.1-8B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| Berkeley Function Calling Leaderboard | — | 25.8% |
| τ²-bench Banking | 25% | — |
| BALROG | — | 15.1% |
Reasoning Inkling leads
Inkling: 40.4 (#56), Llama 3.1-8B: 14.9 (#321)
| Benchmark | Inkling | Llama 3.1-8B |
|---|---|---|
| CritPt | 5.4% | 0% |
| Chess Puzzles | 21% | 0% |
| LMArena Hard Prompts | 1451 | 1175 |
| DTBench | 87.5% | 50.9% |
| LMCA | 37.6% | 5.4% |
| Epoch Capabilities Index | 148.54 | 116.57 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| PIQA | — | 81.2% |
Math Inkling leads
Inkling: 31.3 (#225), Llama 3.1-8B: 10.2 (#317)
| Benchmark | Inkling | Llama 3.1-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 1.7% |
| LMArena Math | 1479 | 1179 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| Omni-MATH | — | 13.7% |
| MATH Level 5 | — | 22.9% |
| GSM8K | — | 82.4% |
Knowledge Inkling leads
Inkling: 55.1 (#49), Llama 3.1-8B: 8.0 (#307)
| Benchmark | Inkling | Llama 3.1-8B |
|---|---|---|
| GPQA Diamond | 88.3% | 27% |
| LMArena Expert | 1465 | 1144 |
| SimpleQA Verified | 40.3% | — |
| MMLU-Pro | — | 40.6% |
| GPQA (HELM) | — | 24.7% |
| BoolQ | — | 82.8% |
| MMLU | — | 56.1% |
Multilingual Inkling leads
Inkling: 54.0 (#52), Llama 3.1-8B: 34.0 (#249)
| Benchmark | Inkling | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1434 | 1148 |
| LMArena Chinese | 1490 | 1151 |
| LMArena French | 1458 | 1177 |
| LMArena German | 1446 | 1144 |
| LMArena Japanese | 1429 | 1061 |
| LMArena Korean | 1404 | 1053 |
| LMArena Russian | 1429 | 1158 |
| LMArena Spanish | 1448 | 1169 |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Llama 3.1-8B: 58.9 (#258)
| Benchmark | Inkling | Llama 3.1-8B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1159 |
| IFEval | — | 74.3% |
Long Context Inkling leads
Inkling: 43.8 (#86), Llama 3.1-8B: 35.8 (#238)
| Benchmark | Inkling | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1434 | 1182 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Llama 3.1-8B: 29.7 (#290)
| Benchmark | Inkling | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1441 | 1187 |
| LMArena Creative Writing | 1387 | 1154 |
| EQ-Bench Creative Writing | 1611 | 713 |
| LMArena Multi-Turn | 1436 | 1172 |
| WildBench | — | 68.7% |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Llama 3.1-8B?
Inkling is the stronger model overall, scoring 44.1 to 23.0 on the Noometry Index. Llama 3.1-8B costs 45× 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 3.1-8B?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Llama 3.1-8B better for coding?
Inkling scores higher on coding benchmarks: 34.5 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Llama 3.1-8B does, with 128K tokens against 66K.
How many benchmarks do Inkling and Llama 3.1-8B share?
27 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Llama 3.1-8B has 43.