Compare Models

Select models (max 5)
Claude Sonnet 5.5Gemini 3.8 Flash
Benchmarks

Vals Index *

Claude Sonnet 5.5
0.00%± 0.96
(66/66)
Gemini 3.8 Flash
0.00%± 1.01
(66/66)

Legal Research Bench *

Claude Sonnet 5.5
0.00%± 3.47
(69/69)
Gemini 3.8 Flash
0.00%± 3.39
(69/69)

Finance Agent (v2) *

Claude Sonnet 5.5
0.00%± 0.67
(70/70)
Gemini 3.8 Flash
0.00%± 0.13
(70/70)

Tax Agent Bench *

Claude Sonnet 5.5
0.00%± 2.98
(61/61)
Gemini 3.8 Flash
0.00%± 3.15
(61/61)

MedCode *

Claude Sonnet 5.5
0.00%± 2.12
(102/102)
Gemini 3.8 Flash
0.00%± 2.18
(102/102)

Terminal-Bench Science

Claude Sonnet 5.5
0.00%± 5.86
(33/33)
Gemini 3.8 Flash
0.00%± 3.37
(33/33)

Code Migration *

Claude Sonnet 5.5
0.00%± 4.26
(69/69)
Gemini 3.8 Flash
0.00%± 4.18
(69/69)

Terminal-Bench 4.0

Claude Sonnet 5.5
0.00%± 1.51
(37/37)
Gemini 3.8 Flash
0.00%± 2.52
(37/37)

Vibe Code Bench v1.1 *

Claude Sonnet 5.5
0.00%± 1.26
(104/104)
Gemini 3.8 Flash
0.00%± 3.88
(104/104)

Overall performance

Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law

2026-09-27

Comparison by Industry

Model performance on different sections of the economy.

Vals Index
69.22%
41.09%
Legal
25.50%
45.31%
Finance
69.07%
68.04%
Healthcare
72.01%
66.32%
Math
100.00%
48.00%
Science
56.26%
35.76%
Academic
N/A
91.25%
Education
51.77%
35.06%
Coding
74.58%
48.06%
Beta
44.87%
22.25%
Social Mobility
67.19%
65.29%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
$20.80
$5.392
Cost / TestVals Index
$20.80
$5.392
Input Cost/ 1M Tokens
$2.00
$1.50
Input Cache Write/ 1M Tokens
$2.50
N/A
Input Cache Read/ 1M Tokens
$0.20
$0.15
Output Cost/ 1M Tokens
$10.00
$7.50

Model Metadata

Basic information about each model.

Model provider
AnthropicAnthropic
GoogleGoogle
Latency4207.12s2692.68s
Cost (In/Out)$2 / $10$1.5 / $7.5
Context Window1M1M
Max Output Token128k66k
Input Modality