Benchmarks · composite
Vals Multimodal Index v1.2
Benchmark consisting of a weighted performance across finance, coding, and education tasks. Showing the potential impact that LLM's can have on the economy. Scores are the values published by VALS AI. Source benchmark version 1.2.
26 models · 26 results · updated 2026-08-11 · vals.ai ↗
Leaderboard
Fable 5 max
More from this benchmark
8 published measuresTime per task33 results · lower is better
Score vs any published measure7 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | |||||||
|---|---|---|---|---|---|---|---|
| Fable 5 max | 56.3 | 71.6 | 97.1 | 80.5 | 93.5 | 51.9 | 68.9 |
| Opus 5 max | 56.6 | 74.9 | 95.1 | 84.6 | 85.7 | 49.4 | 72.1 |
| Kimi K3 max | 55.9 | 72.6 | 95.1 | 80.9 | 91.3 | 54.3 | 66.3 |
| GPT-5.6 Sol max | 55.0 | 66.4 | 99.0 | 85.8 | 89.3 | 52.6 | 67.3 |
| Opus 4.8 max | 53.9 | 66.0 | 89.2 | 71.9 | 89.9 | 54.8 | 69.9 |
| Muse Spark 1.2 max | 59.4 | 72.7 | 85.3 | 69.7 | 82.9 | 47.7 | 65.4 |
| GPT-5.6 Luna max | 55.6 | 65.0 | 93.1 | 79.0 | 81.1 | 44.2 | 67.3 |
| Sonnet 5 max | 52.0 | 67.9 | 75.5 | 74.5 | 86.9 | 48.9 | 70.0 |
| GPT-5.5 xhigh | 51.8 | 69.6 | 82.6 | 76.4 | 77.1 | 51.5 | 68.8 |
| Opus 4.7 high | 51.5 | 66.1 | 82.4 | 68.5 | 77.7 | 56.1 | 70.3 |
| Muse Spark 1.1 xhigh | 57.1 | 73.1 | 78.4 | 69.3 | 72.4 | 45.6 | 66.1 |
| Qwen 3.8 Max | 48.7 | 67.4 | 87.3 | 67.4 | 74.9 | 51.3 | 64.0 |
| Gemini 3.6 Flash high | 55.3 | 63.5 | 77.5 | 73.8 | 69.9 | 48.7 | 67.6 |
| GPT-5.6 Terra xhigh | 52.6 | 66.4 | 73.5 | 73.4 | 72.8 | 47.0 | 67.3 |
| Grok 4.5 high | 48.8 | 68.4 | 86.3 | 67.8 | 72.8 | 35.0 | 61.8 |
| Gemini 3.5 Flash high | 58.1 | 64.6 | 75.5 | 74.2 | 54.7 | 49.9 | 68.1 |
| Sonnet 4.6 max | 51.0 | 66.7 | 77.5 | 57.3 | 56.2 | 46.6 | 67.7 |
| MiniMax M3 max | 48.0 | 69.7 | 69.6 | 53.6 | 56.5 | 50.6 | 68.4 |
| Kimi K2.6 max | 44.9 | 68.2 | 74.5 | 53.6 | 42.3 | 50.2 | 65.8 |
| Qwen 3.7 Plus high | 41.2 | 62.0 | 66.7 | 52.8 | 46.9 | 39.3 | 66.2 |
| MiMo V2.5 xhigh | 37.6 | 60.1 | 64.7 | 60.7 | 48.1 | 43.3 | 59.3 |
| Qwen 3.6 Plus max | 40.9 | 62.2 | 70.6 | 53.2 | 28.3 | 44.9 | 68.0 |
| Inkling Small max | 42.4 | 69.8 | 75.5 | 55.1 | 19.0 | 32.7 | 62.3 |
| Inkling max | 46.0 | 69.2 | 75.5 | 47.6 | 13.3 | 36.6 | 64.0 |
| Grok 4.3 high | 37.8 | 70.0 | 70.6 | 41.9 | 15.5 | 19.7 | 48.3 |
All results
26 rows| # | Model | Effort | Score | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Fable 5 | max | 74.2% | $0.90 | $7.97 | 13 min |
| 2 | Opus 5 | max | 73.9% | $0.11 | $6.14 | 14 min |
| 3 | Kimi K3 | max | 73.4% | $0.13 | $1.70 | 15 min |
| 4 | GPT-5.6 Sol | max | 72.6% | $0.30 | $5.36 | 9.2 min |
| 5 | Opus 4.8 | max | 70.9% | $0.095 | $5.46 | 16 min |
| 6 | Muse Spark 1.2 | max | 69.8% | $0.51 | $0.51 | 7.4 min |
| 7 | GPT-5.6 Luna | max | 69.1% | $0.015 | $0.16 | 6.8 min |
| 8 | Sonnet 5 | max | 68.8% | $0.11 | $6.53 | 17 min |
| 9 | GPT-5.5 | xhigh | 68.1% | $0.18 | $3.32 | 8.4 min |
| 10 | Opus 4.7 | high | 67.4% | $4.44 | $4.44 | 9.4 min |
| 11 | Muse Spark 1.1 | xhigh | 66.7% | $0.36 | $0.36 | 4.8 min |
| 12 | Qwen 3.8 Max | max | 65.4% | $1.93 | $1.93 | 33 min |
| 13 | Gemini 3.6 Flash | high | 65.1% | $0.032 | $1.02 | 8.9 min |
| 14 | GPT-5.6 Terra | xhigh | 65.1% | $0.044 | $0.80 | 4.3 min |
| 15 | Grok 4.5 | high | 63.4% | $0.14 | $0.91 | 5.3 min |
| 16 | Gemini 3.5 Flash | high | 62.9% | $1.01 | $1.01 | 4.4 min |
| 17 | Sonnet 4.6 | max | 60.6% | $1.58 | $1.58 | 8.9 min |
| 18 | MiniMax M3 | max | 60.0% | $0.18 | $1.08 | 18 min |
| 19 | Kimi K2.6 | max | 56.4% | $0.52 | $0.52 | 15 min |
| 20 | Qwen 3.7 Plus | high | 53.9% | $0.40 | $0.26 | 10 min |
| 21 | MiMo V2.5 | xhigh | 52.8% | $0.029 | $0.029 | 7.2 min |
| 22 | Qwen 3.6 Plus | max | 51.5% | $1.12 | $1.12 | 11 min |
| 23 | Inkling Small | max | 50.1% | free | $0.14 | 12 min |
| 24 | Inkling | max | 49.4% | free | $0.63 | 15 min |
| 25 | Grok 4.3 | high | 43.3% | $0.50 | $0.50 | 5.7 min |
| 26 | Mistral Medium 3.5 | high | 34.8% | $0.45 | $3.45 | 12 min |