Up to four models
Qwen3.8-27B vs Inkling-Small
On the index (GPT-4 = 100), Qwen3.8-27B scores 155 and Inkling-Small 153. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
155139–171
WeightsOpen
ReleasedAug 2026
Price in / out$0.060 / $2.2
Context1.02M
Core tests taken3 of 9
TMInkling-Small
153137–169
WeightsOpen
ReleasedJul 2026
Price in / out$0.45 / $1.2
Context524K
Core tests taken5 of 9
Qwen3.8-27B and Inkling-Small are too close to call (2 points apart, within the uncertainty), ahead on 2 of 2 shared core tests, at a similar price.
Test by testthird-party results
Every result as a table
| Test | Qwen3.8-27B | Inkling-Small |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 88.9% | 83.6% |
| MMLU Pro | 84.3% | 85.6% |
| Maths | ||
| ProofBench v1.1 | 16.0% | 6.0% |
| Coding | ||
| Code Migration | 14.2% | 13.7% |
| CyberBench v1.1 | 67.8% | 64.1% |
| IOI | 39.1% | 9.3% |
| LiveCodeBench | 84.0% | 85.9% |
| ProgramBench | 0.0% | 0.5% |
| SWE-bench | 86.0% | 82.2% |
| Vibe Code Bench v1.1 | 64.8% | 19.1% |
| Agents | ||
| SkillsBench | 38.1% | 33.6% |
| Professional work | ||
| Finance Agent (v2) | 48.5% | 41.3% |
| EMB | 59.7% | 31.8% |
| LegalBench | 82.4% | 83.0% |
| Legal Research Bench | 36.1% | 25.5% |
| MedCode | 28.7% | 37.9% |
| MedScribe | 83.9% | 84.1% |
| MortgageTax | 64.9% | 62.3% |
| Tax Agent Bench | 30.9% | 15.4% |
| TaxEval v2 | 70.9% | 75.5% |
| Novel problems | ||
| ARC-AGI-2 | 42.4% | 40.1% |
| ARC-AGI-1 | 87.5% | 84.0% |
Tests at least two of these models have taken. Bold rows are the core tests.