Model comparison
Inkling-Small vs Llama 4 Maverick
Inkling-Small is the stronger model overall, scoring 46.5 to 30.9 on the Noometry Index. Llama 4 Maverick costs 2.1× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
MetaSummary
- They share 26 benchmarks with published results for both. Inkling-Small scores higher in 9 categories and Llama 4 Maverick in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 10.1.
- The biggest single-benchmark swing is ARC-AGI-1: 84% for Inkling-Small and 4.4% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 128K.
Side by side
| Inkling-Small | Llama 4 Maverick | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 46.5 | 30.9 |
| Released | 2026-07-15 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 524K | 128K |
| Max output | 1.05M | 4K |
| Input $ / M tokens | $0.45 | $0.19 |
| Output $ / M tokens | $1.20 | $0.65 |
| Results tracked | 33 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Llama 4 Maverick: 26.6 (#324)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| SciCode | 48.7% | 33.1% |
| LMArena Coding | 1451 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| LMArena WebDev | 1409 | — |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Not comparable
Inkling-Small: —, Llama 4 Maverick: 28.2 (#91)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Llama 4 Maverick: 10.1 (#342)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| ARC-AGI-2 | 40.1% | 0% |
| ARC-AGI-1 | 84% | 4.4% |
| CritPt | 8.3% | 0% |
| LMArena Hard Prompts | 1423 | 1281 |
| Epoch Capabilities Index | 150.15 | 132.2 |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| Chess Puzzles | 18% | — |
| EnigmaEval | — | 0.6% |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| ForecastBench | — | 57.5 |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Llama 4 Maverick: 26.0 (#262)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 20.6% |
| LMArena Math | 1459 | 1299 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Llama 4 Maverick: 33.4 (#204)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 88.5% | 67% |
| LMArena Expert | 1442 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| SimpleQA Verified | 19.1% | — |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
Multimodal Inkling-Small leads
Inkling-Small: 39.1 (#62), Llama 4 Maverick: 31.6 (#105)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1235 | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), Llama 4 Maverick: 42.2 (#195)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1402 | 1269 |
| LMArena Chinese | 1465 | 1277 |
| LMArena French | 1436 | 1259 |
| LMArena German | 1405 | 1291 |
| LMArena Japanese | 1405 | 1207 |
| LMArena Korean | 1363 | 1203 |
| LMArena Russian | 1391 | 1286 |
| LMArena Spanish | 1428 | 1293 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.8 (#114), Llama 4 Maverick: 71.7 (#146)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1399 | 1267 |
| IFEval | — | 90.8% |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#118), Llama 4 Maverick: 31.4 (#279)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1401 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), Llama 4 Maverick: 38.8 (#252)
| Benchmark | Inkling-Small | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1414 | 1287 |
| LMArena Creative Writing | 1331 | 1267 |
| EQ-Bench Creative Writing | 1491 | 860 |
| LMArena Multi-Turn | 1418 | 1289 |
| Short-Story Creative Writing | — | 62% |
| WildBench | — | 80% |
Frequently asked questions
Is Inkling-Small better than Llama 4 Maverick?
Inkling-Small is the stronger model overall, scoring 46.5 to 30.9 on the Noometry Index. Llama 4 Maverick costs 2.1× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Llama 4 Maverick?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Inkling-Small or Llama 4 Maverick better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 128K.
How many benchmarks do Inkling-Small and Llama 4 Maverick share?
26 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Llama 4 Maverick has 54.