Inkling 2 Small
| Released | 2026-11-05 |
|---|---|
| Price per 1M | $0.000 in · $0.000 out |
| Overall score | 58.8 · rank 40 |
| Context window | 1,048,576 tokens |
| Provider | Thinking Machines |
| Weights | Proprietary (Proprietary) |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 58.8 | 40 | 19 |
| Overall: Coding | 58.8 | 41 | 17 |
| Overall: Reasoning | 63.3 | 16 | 4 |
| Overall: Agentic work | 59.4 | 36 | 15 |
| Overall: Frontend | 58.8 | 34 | 5 |
| Coding | 57.6 | 50 | 3 |
| Agents | 59.0 | 40 | 9 |
| Reasoning | 64.0 | 17 | 3 |
| Knowledge | 61.9 | 17 | 1 |
| Frontend | 59.5 | 25 | 2 |
| General | 50.2 | 105 | 1 |
Buzz
| Posts on X | About 44 a day |
|---|---|
| Mood | 45% positive, 0% negative |
| Hacker News | 6 mentions this week |
| Checked | 2026-11-11 |
- Inkling 2 Small is now free on OpenCode for a limited time - 1M Context - Multi-modal - 594B MoE, 17B active Limited to certain regions
- New in DesignArena: Claude Fable 5.2 by @AnthropicAI lands at #1 on 3D Design Arena with an Elo of 1540 and 81% win rate, replacing GPT-6 Astra (max) by @OpenAI. The second best Anthropic model on 3D Design arena is Opus 5.5 in 3rd place, which is followed by Inkling 2 Small b…
- FREE AI: DeepSeek, Claude Haiku, GPT-6 Luna and 1M context Inkling, all at $0 this week > CanTrustAI: free models with no monthly limit, including DeepSeek V4.1 Flash, Claude Haiku 5.5, GPT-6 Luna and Seedream. paid models at 50-75% off. 1,000 welcome credits with Google: https…
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 58.5 ±2.1 | 17 |
| Extra High | 64.5 ±5.7 | 2 |
Evidence
Coding 57.6 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SciCode | 52.3% | Epoch AI | 2026-11-11 |
| SWE-bench Multimodal | 43.1% | Vals AI | 2026-11-09 |
| ProgramBench | 0.5% | Vals AI | 2026-11-09 |
Agents 59.0 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 12.6% | Vals AI | 2026-11-09 |
| SRE Bench | 1.9% | Vals AI | 2026-11-05 |
| Terminal-Bench-Science | 2.9% | Vals AI | 2026-11-09 |
| APEX-Agents | 46.8% | Epoch AI | 2026-11-11 |
| EMB v1.1 (Excel financial modeling) | 69.5% | Vals AI | 2026-11-09 |
| Tax Agent Bench | 38.9% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 67.5% | Vals AI | 2026-11-09 |
| HLAB-Vals 1.1 (legal agent) | 21.7% | Vals AI | 2026-11-09 |
| CyberBench v1.1 | 72.7% | Vals AI | 2026-11-05 |
Reasoning 64.0 ±4.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| BioMysteryBench | 70.0% | Vals AI | 2026-11-09 |
| ARC-AGI-2 | 81.7% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 96.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 96.5% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 81.7% | ARC Prize | 2026-11-11 |
Knowledge 61.9 ±6.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Legal Research Bench | 46.6% | Vals AI | 2026-11-09 |
Frontend 59.5 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 81.5% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,649 | LMArena | 2026-11-09 |
General 50.2 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,412 | LMArena | 2026-11-09 |
Names matched to this model
inkling-2-small