Compare Models
Select models (max 5)
Claude Fable 5.1Gemini 3.8 Flash
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 65.83%±1.11 | 54.83%±1.03 |
| Legal Research BenchAgentic US legal research | 55.29%±3.46 | 38.94%±3.39 |
| Finance Agent (v2)Core financial analyst tasks | 58.88%±2.06 | 61.44%±0.13 |
| Tax Agent BenchAgentic US corporate tax research | 77.64%±2.83 | 66.77%±3.15 |
| MedCodeMedical billing code support | 53.51%±2.17 | 48.13%±2.18 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 40.00%±5.90 | 8.57%±3.37 |
| Code MigrationRewriting programs in new languages | 54.61%±4.81 | 36.55%±4.18 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 58.08%±3.31 | 19.19%±2.52 |
| Vibe Code Bench v1.1Building web apps from scratch | 90.26%±1.57 | 78.65%±3.88 |
Benchmarks
Vals Index *
Claude Fable 5.1
0.00%± 1.11
(43/43)Gemini 3.8 Flash
0.00%± 1.03
(43/43)Legal Research Bench *
Claude Fable 5.1
0.00%± 3.46
(73/73)Gemini 3.8 Flash
0.00%± 3.39
(73/73)Finance Agent (v2) *
Claude Fable 5.1
0.00%± 2.06
(74/74)Gemini 3.8 Flash
0.00%± 0.13
(74/74)Tax Agent Bench *
Claude Fable 5.1
0.00%± 2.83
(65/65)Gemini 3.8 Flash
0.00%± 3.15
(65/65)MedCode *
Claude Fable 5.1
0.00%± 2.17
(104/104)Gemini 3.8 Flash
0.00%± 2.18
(104/104)Terminal-Bench Science
Claude Fable 5.1
0.00%± 5.90
(38/38)Gemini 3.8 Flash
0.00%± 3.37
(38/38)Code Migration *
Claude Fable 5.1
0.00%± 4.81
(73/73)Gemini 3.8 Flash
0.00%± 4.18
(73/73)Terminal-Bench 4.0
Claude Fable 5.1
0.00%± 3.31
(43/43)Gemini 3.8 Flash
0.00%± 2.52
(43/43)Vibe Code Bench v1.1 *
Claude Fable 5.1
0.00%± 1.57
(108/108)Gemini 3.8 Flash
0.00%± 3.88
(108/108)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-02
Comparison by Industry
Model performance on different sections of the economy.
Legal
50.16%
vs.45.31%
Finance
71.99%
vs.68.04%
Healthcare
72.40%
vs.66.32%
Math
100.00%
vs.48.00%
Science
43.87%
vs.35.76%
Academic
92.15%
vs.91.25%
Education
48.53%
vs.35.06%
Coding
60.10%
vs.48.73%
Cyber
46.66%
vs.43.75%
Social Mobility
74.90%
vs.65.29%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$28.71
$5.729
Cost / TestVals Index
$28.71
vs.$5.729
Input Cost/ 1M Tokens
$10.00
vs.$1.50
Input Cache Write/ 1M Tokens
$12.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.25
vs.$0.15
Output Cost/ 1M Tokens
$50.00
vs.$7.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Google |
| Latency | 4608.95s | 3117.16s |
| Cost (In/Out) | $10 / $50 | $1.5 / $7.5 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 66k |
| Input Modality |