Inkling
| Released | 2026-07-15 |
|---|---|
| Price per 1M | $1.87 in · $4.68 out |
| Overall score | 53.3 · rank 88 |
| Context window | 1,048,576 tokens |
| Provider | Thinking Machines |
| Weights | Open weights (Apache-2.0) |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 53.3 | 88 | 47 |
| Overall: Coding | 51.9 | 93 | 35 |
| Overall: Reasoning | 54.1 | 83 | 15 |
| Overall: Agentic work | 53.7 | 85 | 32 |
| Overall: Frontend | 47.7 | 114 | 14 |
| Coding | 52.4 | 101 | 10 |
| Agents | 53.6 | 85 | 14 |
| Reasoning | 56.2 | 75 | 8 |
| Math | 51.8 | 96 | 4 |
| Knowledge | 53.7 | 71 | 3 |
| Frontend | 44.8 | 94 | 3 |
| General | 57.2 | 44 | 4 |
| Multimodal | 50.8 | 70 | 1 |
| Value vs price | +2.7 | 100 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 52.7 ±0.9 | 37 |
| Max | 54.8 ±6.1 | 1 |
| Extra High | 53.8 ±3.0 | 10 |
Evidence
Coding 52.4 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierSWE | 4.1% | Epoch AI | 2026-11-11 |
| FrontierCode | 14.0% | Epoch AI | 2026-11-11 |
| Code Migration v1.1 | 8.8% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Coding | 48.7% | LiveBench | 2026-11-06 |
| WeirdML v3 | 3.9% | Epoch AI | 2026-11-11 |
| IOI | 14.9% | Vals AI | 2026-10-29 |
| SWE-bench Verified (Vals run) | 77.6% | Vals AI | 2026-09-01 |
| SciCode | 47.0% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 85.5% | Vals AI | 2026-09-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 53.6 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 0.5% | Vals AI | 2026-11-09 |
| SRE Bench | 0.0% | Vals AI | 2026-11-05 |
| APEX-Agents | 33.8% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Agentic | 9.8% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 12.0% | LiveBench | 2026-11-06 |
| Terminal-Bench 2.1 (Vals run) | 47.6% | Vals AI | 2026-10-01 |
| tau2-bench Banking Knowledge | 25.0% | tau2-bench | 2026-07-24 |
| EMB v1.1 (Excel financial modeling) | 41.0% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Research | 60.3% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 15.3% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 49.9% | Vals AI | 2026-11-09 |
| SkillsBench | 26.1% | Vals AI | 2026-10-29 |
| HLAB-Vals 1.1 (legal agent) | 3.8% | Vals AI | 2026-11-09 |
| CyberBench v1.1 | 66.8% | Vals AI | 2026-11-05 |
Reasoning 56.2 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 36.5% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 36.5% | ARC Prize | 2026-11-11 |
| CritPt | 5.4% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 79.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 79.5% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 88.3% | Epoch AI | 2026-08-05 |
| GPQA Diamond (Vals run) | 87.1% | Vals AI | 2026-09-01 |
| Chess Puzzles | 21.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 50.0% | SimpleBench | 2026-07-22 |
| SimpleBench | 50.0% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Reasoning | 78.3% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Data Analysis | 72.8% | LiveBench | 2026-11-06 |
Math 51.8 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 33.3% | Epoch AI | 2026-08-06 |
| FrontierMath Tier 4 | 4.9% | Epoch AI | 2026-08-06 |
| OTIS Mock AIME 2024-2025 | 88.9% | Epoch AI | 2026-08-05 |
| ProofBench v1.1 | 0.0% | Vals AI | 2026-11-09 |
| ProofBench | 0.0% | Epoch AI | 2026-11-11 |
Knowledge 53.7 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 40.3% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 86.3% | Vals AI | 2026-09-01 |
| Legal Research Bench | 28.4% | Vals AI | 2026-11-09 |
Frontend 44.8 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 55.2% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 19.2% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,414 | LMArena | 2026-11-09 |
General 57.2 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench 4 | 1,212 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 1,609 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,443 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 72.5% | EQ-Bench | 2026-11-11 |
Multimodal 50.8 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 78.5% | Vals AI | 2026-09-01 |
Names matched to this model
inkling, inkling-peft-262144, inkling-peft-262144-sampling-nvfp4