Benchmarks · economics
MortgageTax (Vals)
Evaluating reading and understanding tax certificates as images Scores are the values published by VALS AI. Source benchmark version 1.
37 models · 37 results · updated 2026-09-01 · vals.ai ↗
Leaderboard
Opus 5 max
Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 23 more models under All models in settings.
More from this benchmark
3 published measuresTime per task97 results · lower is better
24 more models under All models in settings.
Score vs any published measure2 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | ||
|---|---|---|
| Opus 5 max | 62.7 | 81.4 |
| Fable 5.1 max | 64.0 | 77.6 |
| Opus 4.7 max | 61.8 | 78.7 |
| Sonnet 5 max | 61.4 | 78.7 |
| Opus 4.8 max | 60.1 | 79.7 |
| Fable 5 max | 61.1 | 76.7 |
| Gemini 2.5 Pro high | 60.3 | 77.6 |
| GPT-5.5 xhigh | 61.4 | 76.2 |
| Gemini 3.5 Flash-Lite high | 61.5 | 75.8 |
| MiniMax M3 max | 59.5 | 77.3 |
| Qwen 3.6 27B max | 60.8 | 75.8 |
| Gemini 3.5 Flash high | 58.7 | 77.5 |
| Qwen 3.6 Plus max | 57.8 | 78.1 |
| Sonnet 4.6 max | 60.5 | 75.0 |
| Gemini 3.6 Flash high | 58.4 | 76.8 |
| Qwen 3.5 Flash max | 59.8 | 75.0 |
| GPT-5.6 Terra xhigh | 60.3 | 74.3 |
| GPT-5.6 Luna max | 59.0 | 75.6 |
| GPT-5.6 Sol max | 59.5 | 75.1 |
| Gemini 3.7 Flash high | 57.6 | 75.7 |
| Kimi K3 max | 53.8 | 78.9 |
| Qwen 3.7 Plus high | 57.6 | 74.8 |
| Muse Spark 1.1 xhigh | 57.8 | 74.5 |
| Kimi K2.6 max | 57.2 | 74.5 |
| Muse Spark 1.2 xhigh | 57.2 | 73.6 |
All results
37 rows| # | Model | Effort | MortgageTax (Vals) | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Opus 5 | max | 72.1% | $0.001 | $0.074 | 8.0s |
| 2 | Fable 5.1 | max | 70.8% | $0.027 | $0.17 | 15s |
| 3 | Opus 4.7 | max | 70.3% | $0.084 | $0.084 | 16s |
| 4 | Sonnet 5 | max | 70.0% | $0.001 | $0.080 | 29s |
| 5 | Opus 4.8 | max | 69.9% | $0.002 | $0.11 | 21s |
| 6 | Fable 5 | max | 68.9% | $0.020 | $0.18 | 16s |
| 7 | Gemini 2.5 Pro | high | 68.9% | $0.005 | $0.005 | 24s |
| 8 | GPT-5.5 | xhigh | 68.8% | $0.002 | $0.071 | 28s |
| 9 | Gemini 3.5 Flash-Lite | high | 68.7% | $0.004 | $0.004 | 4.9s |
| 10 | MiniMax M3 | max | 68.4% | $0.001 | $0.008 | 27s |
| 11 | Qwen 3.6 27B | max | 68.3% | $0.017 | $0.017 | 42s |
| 12 | Gemini 3.5 Flash | high | 68.1% | $0.018 | $0.018 | 11s |
| 13 | Qwen 3.6 Plus | max | 68.0% | $0.007 | $0.013 | 78s |
| 14 | Sonnet 4.6 | max | 67.7% | $0.045 | $0.045 | 30s |
| 15 | Gemini 3.6 Flash | high | 67.6% | $0.001 | $0.020 | 9.2s |
| 16 | Qwen 3.5 Flash | max | 67.4% | $0.002 | $0.002 | 37s |
| 17 | GPT-5.6 Terra | xhigh | 67.3% | $0.001 | $0.023 | 6.3s |
| 18 | GPT-5.6 Luna | max | 67.3% | $0.000 | $0.005 | 23s |
| 19 | GPT-5.6 Sol | max | 67.3% | $0.002 | $0.071 | 13s |
| 20 | Gemini 3.7 Flash | high | 66.7% | $0.001 | $0.011 | 4.1s |
| 21 | Kimi K3 | max | 66.3% | $0.004 | $0.039 | 79s |
| 22 | Qwen 3.7 Plus | high | 66.2% | $0.012 | $0.008 | 61s |
| 23 | Muse Spark 1.1 | xhigh | 66.1% | $0.022 | $0.022 | 25s |
| 24 | Kimi K2.6 | max | 65.8% | $0.014 | $0.029 | 1.8 min |
| 25 | Muse Spark 1.2 | xhigh | 65.4% | $0.013 | $0.026 | 45s |
| 26 | Gemini 3.8 Flash | high | 65.3% | $0.002 | $0.047 | 15s |
| 27 | Qwen 3.8 27B | xhigh | 64.9% | $0.001 | $0.012 | 80s |
| 28 | Grok 4.6 | high | 64.2% | $0.001 | $0.014 | 8.5s |
| 29 | Inkling | max | 64.0% | $0.005 | $0.056 | 69s |
| 30 | Qwen 3.8 Max | max | 64.0% | $0.003 | $0.027 | 47s |