Benchmarks · economics
TaxEval (Vals)
A Vals-created set of questions and responses to tax questions Scores are the values published by VALS AI. Source benchmark version 2.
59 models · 59 results · updated 2026-09-01 · vals.ai ↗
Leaderboard
Muse Spark 1.2 xhigh
More from this benchmark
3 published measuresTime per task145 results · lower is better
Score vs any published measure2 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | ||
|---|---|---|
| Muse Spark 1.2 xhigh | 68.0 | 92.7 |
| Muse Spark 1.1 xhigh | 66.9 | 92.6 |
| Muse Spark | 65.6 | 89.8 |
| Sonnet 4.6 max | 65.8 | 88.4 |
| Fable 5 max | 65.8 | 88.1 |
| GPT-5.6 Luna max | 66.6 | 85.8 |
| GPT-5.6 Terra xhigh | 65.8 | 86.5 |
| Fable 5.1 max, fallback | 64.1 | 87.8 |
| Grok 3 none | 63.9 | 87.9 |
| Kimi K3 max | 65.3 | 86.1 |
| Opus 4.8 max | 64.5 | 86.8 |
| Sonnet 5 max | 64.0 | 87.2 |
| GLM 5.3 Flash max | 64.0 | 87.2 |
| Qwen 3.8 Max | 64.1 | 87.0 |
| Inkling Small max | 63.9 | 87.2 |
| Inkling max | 63.5 | 87.1 |
| Qwen 3.7 Max | 63.5 | 87.1 |
| Opus 4.7 max | 63.8 | 86.8 |
| Opus 5 max | 62.0 | 88.3 |
| GPT-5.5 xhigh | 65.5 | 84.5 |
| Gemini 3.6 Flash high | 63.5 | 86.2 |
| GPT-5.6 Sol max | 65.0 | 84.5 |
| Gemini 3.7 Flash high | 63.6 | 85.9 |
| Qwen 3.6 Plus max | 64.2 | 85.3 |
| Kimi K2.6 max | 62.7 | 86.6 |
All results
59 rows| # | Model | Effort | TaxEval (Vals) | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Muse Spark 1.2 | xhigh | 80.4% | $0.007 | $0.014 | 48s |
| 2 | Muse Spark 1.1 | xhigh | 79.7% | $0.015 | $0.015 | 33s |
| 3 | Muse Spark | 77.7% | $0.002 | $0.002 | 58s | |
| 4 | Sonnet 4.6 | max | 77.1% | $0.13 | $0.13 | 2.1 min |
| 5 | Fable 5 | max | 76.9% | $0.025 | $0.22 | 57s |
| 6 | GPT-5.6 Luna | max | 76.2% | $0.001 | $0.012 | 77s |
| 7 | GPT-5.6 Terra | xhigh | 76.2% | $0.002 | $0.036 | 37s |
| 8 | Fable 5.1 | max | 76.0% | $0.054 | $0.35 | 86s |
| 9 | Grok 3 | none | 75.9% | $0.017 | $0.017 | 13s |
| 10 | Kimi K3 | max | 75.7% | $0.006 | $0.078 | 2.4 min |
| 11 | Opus 4.8 | max | 75.6% | $0.003 | $0.16 | 70s |
| 12 | Sonnet 5 | max | 75.6% | $0.005 | $0.30 | 3.4 min |
| 13 | GLM 5.3 Flash | max | 75.6% | free | $0.002 | 53s |
| 14 | Qwen 3.8 Max | max | 75.6% | $0.076 | $0.076 | 4.4 min |
| 15 | Inkling Small | max | 75.5% | free | $0.018 | 4.0 min |
| 16 | Inkling | max | 75.3% | free | $0.10 | 3.3 min |
| 17 | Qwen 3.7 Max | max | 75.3% | $0.009 | $0.028 | 58s |
| 18 | Opus 4.7 | max | 75.3% | $0.12 | $0.12 | 62s |
| 19 | Opus 5 | max | 75.1% | $0.002 | $0.11 | 58s |
| 20 | GPT-5.5 | xhigh | 75.0% | $0.003 | $0.060 | 1.6 min |
| 21 | Gemini 3.6 Flash | high | 74.9% | $0.001 | $0.020 | 12s |
| 22 | GPT-5.6 Sol | max | 74.8% | $0.008 | $0.14 | 62s |
| 23 | Gemini 3.7 Flash | high | 74.7% | $0.002 | $0.019 | 7.8s |
| 24 | Qwen 3.6 Plus | max | 74.7% | $0.011 | $0.011 | 71s |
| 25 | Kimi K2.6 | max | 74.7% | $0.029 | $0.029 | 4.5 min |
| 26 | Gemini 3.8 Flash | high | 74.4% | $0.001 | $0.024 | 8.8s |
| 27 | Gemini 3.5 Flash | high | 74.4% | $0.038 | $0.038 | 20s |
| 28 | MiMo V2.5 Pro | xhigh | 73.8% | $0.000 | $0.003 | 63s |
| 29 | Qwen 3 Max | max | 73.5% | $0.007 | $0.007 | 29s |
| 30 | GLM 5.2 | max | 73.3% | $0.001 | $0.015 | 65s |