Compare Models
Select models (max 7)
Claude Sonnet 5.5Gemini 4 CarbonClaude Opus 5.5Gemini 4 ArgonWonder Full
 |  |  | | |  |
|---|---|---|---|---|---|
| Vals IndexGDP-weighted benchmark | 70.85%±0.93 | 70.45%±0.97 | 70.18%±1.00 | 69.24%±1.09 | 66.79%±1.07 |
| Legal Research BenchAgentic US legal research | 48.08%±3.47 | 55.77%±3.45 | 50.48%±3.48 | 54.81%±3.46 | 53.37%±3.47 |
| Finance Agent v2.1Core financial analyst tasks | 67.28%±2.02 | 67.16%±2.02 | 67.85%±2.05 | 67.66%±2.00 | 67.58%±1.98 |
| Tax Agent BenchAgentic US corporate tax research | 41.96%±3.56 | 51.78%±3.60 | 45.57%±3.59 | 44.56%±3.59 | 43.00%±3.57 |
| MedCodeMedical billing code support | 52.92%±2.12 | N/A | 49.80%±2.27 | 58.80%±2.10 | 49.93%±2.18 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 47.14%±6.01 | N/A | 47.14%±6.01 | 44.29%±5.98 | 37.14%±5.82 |
| Code Migration v1.1Rewriting programs in new languages | 86.88%±1.52 | N/A | 81.01%±3.21 | 70.80%±3.72 | 62.79%±3.17 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 64.14%±1.01 | 63.13%±2.20 | 65.15%±0.00 | 57.58%±2.31 | 58.08%±3.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 92.39%±1.26 | 89.06%±2.29 | 90.29%±1.53 | 91.91%±1.90 | 86.00%±1.93 |
Benchmarks
Vals Index *
Claude Sonnet 5.5
0.00%± 0.93
(33/33)Gemini 4 Carbon
0.00%± 0.97
(33/33)Claude Opus 5.5
0.00%± 1.00
(33/33)Gemini 4 Argon
0.00%± 1.09
(33/33)Wonder Full
0.00%± 1.07
(33/33)Legal Research Bench *
Claude Sonnet 5.5
0.00%± 3.47
(90/90)Gemini 4 Carbon
0.00%± 3.45
(90/90)Claude Opus 5.5
0.00%± 3.48
(90/90)Gemini 4 Argon
0.00%± 3.46
(90/90)Wonder Full
0.00%± 3.47
(90/90)Finance Agent v2.1 *
Claude Sonnet 5.5
0.00%± 2.02
(36/36)Gemini 4 Carbon
0.00%± 2.02
(36/36)Claude Opus 5.5
0.00%± 2.05
(36/36)Gemini 4 Argon
0.00%± 2.00
(36/36)Wonder Full
0.00%± 1.98
(36/36)Tax Agent Bench *
Claude Sonnet 5.5
0.00%± 3.56
(81/81)Gemini 4 Carbon
0.00%± 3.60
(81/81)Claude Opus 5.5
0.00%± 3.59
(81/81)Gemini 4 Argon
0.00%± 3.59
(81/81)Wonder Full
0.00%± 3.57
(81/81)MedCode *
Claude Sonnet 5.5
0.00%± 2.12
(107/107)Gemini 4 Carbon
N/AClaude Opus 5.5
0.00%± 2.27
(107/107)Gemini 4 Argon
0.00%± 2.10
(107/107)Wonder Full
0.00%± 2.18
(107/107)Terminal-Bench-Science
Claude Sonnet 5.5
0.00%± 6.01
(43/43)Gemini 4 Carbon
N/AClaude Opus 5.5
0.00%± 6.01
(43/43)Gemini 4 Argon
0.00%± 5.98
(43/43)Wonder Full
0.00%± 5.82
(43/43)Code Migration v1.1 *
Claude Sonnet 5.5
0.00%± 1.52
(29/29)Gemini 4 Carbon
N/AClaude Opus 5.5
0.00%± 3.21
(29/29)Gemini 4 Argon
0.00%± 3.72
(29/29)Wonder Full
0.00%± 3.17
(29/29)Terminal-Bench 4.0
Claude Sonnet 5.5
0.00%± 1.01
(60/60)Gemini 4 Carbon
0.00%± 2.20
(60/60)Claude Opus 5.5
0.00%± 0.00
(60/60)Gemini 4 Argon
0.00%± 2.31
(60/60)Wonder Full
0.00%± 3.31
(60/60)Vibe Code Bench v1.1 *
Claude Sonnet 5.5
0.00%± 1.26
(124/124)Gemini 4 Carbon
0.00%± 2.29
(124/124)Claude Opus 5.5
0.00%± 1.53
(124/124)Gemini 4 Argon
0.00%± 1.90
(124/124)Wonder Full
0.00%± 1.93
(124/124)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-04
Comparison by Industry
Model performance on different sections of the economy.
Legal
42.49%
vs.36.63%
vs.43.93%
vs.59.57%
vs.58.83%
Finance
71.28%
vs.65.14%
vs.72.31%
vs.62.35%
vs.61.86%
Healthcare
72.01%
vs.N/A
vs.70.61%
vs.73.11%
vs.69.63%
Math
100.00%
vs.N/A
vs.100.00%
vs.99.00%
vs.94.00%
Science
59.12%
vs.N/A
vs.47.63%
vs.41.73%
vs.39.01%
Education
88.03%
vs.N/A
vs.91.30%
vs.89.46%
vs.N/A
Coding
65.22%
vs.76.10%
vs.64.37%
vs.57.15%
vs.52.64%
Cyber
44.87%
vs.N/A
vs.44.47%
vs.61.07%
vs.42.73%
Social Mobility
67.19%
vs.N/A
vs.70.64%
vs.69.76%
vs.73.75%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$18.70
$10.51
$28.12
$13.37
$6.81
Cost / TestVals Index
$18.70
vs.$10.51
vs.$28.12
vs.$13.37
vs.$6.81
Input Cost/ 1M Tokens
$2.00
vs.$4.00
vs.$4.00
vs.$4.00
vs.$4.00
Input Cache Write/ 1M Tokens
$2.50
vs.N/A
vs.$5.00
vs.N/A
vs.N/A
Input Cache Read/ 1M Tokens
$0.10
vs.$0.20
vs.$0.20
vs.$0.20
vs.$0.20
Output Cost/ 1M Tokens
$10.00
vs.$20.00
vs.$20.00
vs.$20.00
vs.$20.00
Model Metadata
Basic information about each model.
| | | | | |
|---|---|---|---|---|---|
| Model provider | Anthropic | Google | Anthropic | Google | Meta |
| Latency | 5158.77s | 2864.86s | 5071.09s | 2697.95s | 3558.57s |
| Cost (In/Out) | $2 / $10 | $4 / $20 | $4 / $20 | $4 / $20 | $4 / $20 |
| Context Window | 1M | 1M | 1M | 1M | 1M |
| Max Output Token | 128k | 1M | 128k | 1M | 131k |
| Input Modality |