Up to four models
Inkling vs Qwen3.7-Plus
On the index (GPT-4 = 100), Inkling scores 149 and Qwen3.7-Plus 148. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
TMInkling
149133–165
WeightsOpen
ReleasedJul 2026
Price in / out$1.0 / $4.05
Context524K
Core tests taken6 of 9
148131–165
WeightsClosed
ReleasedJun 2026
Price in / out$0.32 / $1.28
Context1M
Core tests taken3 of 9
Inkling and Qwen3.7-Plus are too close to call (1 point apart, within the uncertainty), ahead on 2 of 3 shared core tests, at 3.1× the price.
Test by testthird-party results
TMInkling
Qwen3.7-Plus
Every result as a table
| Test | Inkling | Qwen3.7-Plus |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 88.3% | 87.9% |
| Maths | ||
| FrontierMath (tiers 1-3) | 33.3% | 34.4% |
| AIME-style maths (OTIS mock) | 88.9% | 93.3% |
| Coding | ||
| Code Migration | 11.8% | 12.9% |
| Vibe Code Bench v1.1 | 19.2% | 46.4% |
| Agents | ||
| SkillsBench | 26.1% | 54.3% |
| DTBench | 87.5% | 84.0% |
| LMCA | 37.6% | 37.6% |
| Professional work | ||
| Finance Agent (v2) | 46.6% | 38.2% |
| EMB | 38.4% | 49.3% |
| Legal Research Bench | 28.4% | 16.4% |
| MortgageTax | 64.0% | 66.2% |
| Tax Agent Bench | 15.3% | 10.5% |
Tests at least two of these models have taken. Bold rows are the core tests.