Updated daily at 05:00 UTC
Vision-language
Inkling
- Released
- 15 Jul 2026
- Status
- Current
- Context
- 262.1K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- apache-2.0
- Parameters
- 975B, 41B active
- Knowledge cutoff
- —
- Reasoning
- Yes
- Modalities
- text, image, audio → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 33.7 | 46 | 3 of 4 |
| Coding & software engineering | 14.0 | Not ranked | 1 of 5 |
| Factuality & hallucination | 40.3 | 39 | 1 of 1 |
| Human preference | 53.8 | Not ranked | 2 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Chess Puzzles | Puzzles solved | 21.0% | Independent | xhigh | 5 Aug 2026 | Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 87.5% | Third party | xhigh | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| Humanity's Last Exam (HLE) | Accuracy | 46.0% | Self-reported | — | — | Model Card via Hugging Face Community Evals |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.3758 | Third party | xhigh | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| SimpleBench | Score (AVG@5) | 50.0% | Third party | — | — | https://lmcouncil.ai/benchmarks via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 88.3% | Independent | xhigh | 5 Aug 2026 | Epoch AI |
| GPQA Diamond | Accuracy | 87.2% | Self-reported | — | — | Model Card via Hugging Face Community Evals |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tier 4 | Accuracy | 4.9% | Independent | xhigh | 6 Aug 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 33.3% | Independent | xhigh | 6 Aug 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 88.9% | Independent | xhigh | 5 Aug 2026 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierCode | Main score (Mean@5) | 14.0% | Third party | — | — | https://cognition.com/frontiercode via Epoch AI |
| WeirdML (v2) | Average accuracy | 32.3% | Third party | high | — | https://htihle.github.io/weirdml.html via Epoch AI |
Professional knowledge work
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| APEX-Agents | Pass@1 (all rubric criteria met) | 33.8% | Source not stated | — | — | Epoch AI via Epoch AI |
Factuality & hallucination
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| SimpleQA Verified | Accuracy (% correct) | 40.3% | Independent | xhigh | 27 Aug 2026 | Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1411 | Independent | — | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 12520 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1442 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 32778 | Independent | — | 25 Sep 2026 | Arena |
Other Inkling versions
- Inkling Small30 Jul 2026