Inkling vs Inkling-Small
| Spec | Inkling | Inkling-Small |
|---|---|---|
| Respan Index | 31.9 (#85) | 29.4 (#95) |
| Blended price per 1M | $1.76 | $0.237 |
| Context window | 1M | 1M |
| Input / output per 1M | $1 / $4.05 | $0.15 / $0.5 |
| Max output | - | - |
| Input | text, vision, audio | text, vision, audio |
| Released | 2026-07-15 | 2026-07-30 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Inkling | Inkling-Small |
|---|---|---|
| Coding | 6.1 Inkling | 5.7 Inkling-Small |
| Agents | 43.1 Inkling | 41.5 Inkling-Small |
| Reasoning | 31.8 Inkling | 32.2 Inkling-Small |
| Knowledge & language | 39.6 Inkling | 19.1 Inkling-Small |
| Human preference | 51.4 Inkling | 50.9 Inkling-Small |
Benchmarks both report
Inkling leads on 11 of the 21 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| LMArena Elo | 1443 | 1406 |
| LMArena WebDev (LMArena) | 1414 | 1408 |
| LMArena Agent (LMArena) | -0.1845 | -0.1853 |
| Chess Puzzles (Epoch AI) | 21% | 18% |
| FrontierMath Tier 4 v2 (Epoch AI) | 4.9% | 17.1% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 33.3% | 46.3% |
| GPQA Diamond | 88.3% | 88.5% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 88.9% | 90% |
| SAGE (Vals AI) | 36.6% | 32.7% |
| SimpleQA Verified | 43.9% | 20.6% |
| Terminal-Bench 4.0 (Vals AI) | 0.5% | 0% |
| AIME 2026 | 97.1% | 95.5% |
| CharXiv RQ | 78.1% | 77.4% |
| CharXiv RQ (with python) | 82% | 81.3% |
| IFBench | 79.8% | 82.2% |
| MMAU | 77.2% | 77% |
| SWE-bench Pro (public) | 54.3% | 55.9% |
| SWE-bench Verified | 77.6% | 80.2% |
| Terminal-Bench 2.1 (best harness) | 63.8% | 64.7% |
| Toolathlon Verified | 45.5% | 54.4% |
| Toolathlon-Verified (HKUST) | 45.5% | 54.4% |
FAQ
Is Inkling better than Inkling-Small?
Inkling scores 31.9 on the Respan Index (#85), ahead of Inkling-Small at 29.4 (#95). Inkling leads on 11 of the 21 benchmarks both report.
Which is cheaper, Inkling or Inkling-Small?
Inkling lists at $1 input and $4.05 output per 1M tokens; Inkling-Small at $0.15 and $0.5. Inkling-Small is 7.4x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.