Compare Models
Select models (max 5)
Claude Fable 5.1GPT-6 Astra
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 65.83%±1.11 | 63.13%±1.19 |
| Legal Research BenchAgentic US legal research | 55.29%±3.46 | 39.42%±3.40 |
| Finance Agent (v2)Core financial analyst tasks | 58.88%±2.06 | 53.54%±2.08 |
| Tax Agent BenchAgentic US corporate tax research | 77.64%±2.83 | 63.34%±3.15 |
| MedCodeMedical billing code support | 53.51%±2.17 | 48.49%±2.13 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 40.00%±5.90 | 62.86%±5.82 |
| Code MigrationRewriting programs in new languages | 54.61%±4.81 | 67.74%±4.22 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 58.08%±3.31 | 59.60%±4.40 |
| Vibe Code Bench v1.1Building web apps from scratch | 90.26%±1.57 | 89.59%±2.17 |
Benchmarks
Vals Index *
Claude Fable 5.1
0.00%± 1.11
(41/41)GPT-6 Astra
0.00%± 1.19
(41/41)Legal Research Bench *
Claude Fable 5.1
0.00%± 3.46
(72/72)GPT-6 Astra
0.00%± 3.40
(72/72)Finance Agent (v2) *
Claude Fable 5.1
0.00%± 2.06
(73/73)GPT-6 Astra
0.00%± 2.08
(73/73)Tax Agent Bench *
Claude Fable 5.1
0.00%± 2.83
(64/64)GPT-6 Astra
0.00%± 3.15
(64/64)MedCode *
Claude Fable 5.1
0.00%± 2.17
(104/104)GPT-6 Astra
0.00%± 2.13
(104/104)Terminal-Bench Science
Claude Fable 5.1
0.00%± 5.90
(34/34)GPT-6 Astra
0.00%± 5.82
(34/34)Code Migration *
Claude Fable 5.1
0.00%± 4.81
(71/71)GPT-6 Astra
0.00%± 4.22
(71/71)Terminal-Bench 4.0
Claude Fable 5.1
0.00%± 3.31
(42/42)GPT-6 Astra
0.00%± 4.40
(42/42)Vibe Code Bench v1.1 *
Claude Fable 5.1
0.00%± 1.57
(106/106)GPT-6 Astra
0.00%± 2.17
(106/106)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-09-30
Comparison by Industry
Model performance on different sections of the economy.
Legal
50.16%
vs.22.42%
Finance
71.99%
vs.62.86%
Healthcare
72.40%
vs.68.20%
Math
100.00%
vs.99.00%
Science
43.87%
vs.65.09%
Academic
92.15%
vs.N/A
Education
48.53%
vs.46.37%
Coding
60.10%
vs.58.35%
Cyber
46.66%
vs.48.97%
Social Mobility
74.90%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$28.71
$18.46
Cost / TestVals Index
$28.71
vs.$18.46
Input Cost/ 1M Tokens
$10.00
vs.$10.00
Input Cache Write/ 1M Tokens
$12.50
vs.$12.50
Input Cache Read/ 1M Tokens
$0.25
vs.$1.00
Output Cost/ 1M Tokens
$50.00
vs.$50.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | OpenAI |
| Latency | 4608.95s | 1667.74s |
| Cost (In/Out) | $10 / $50 | $10 / $50 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |