Compare Models
Select models (max 7)
Claude Opus 4.8Gemini 3.8 Flash
| Vals IndexGDP-weighted benchmark | N/A | 55.95%±1.14 |
| Legal Research BenchAgentic US legal research | 43.75%±3.45 | 38.94%±3.39 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 65.76%±2.04 |
| Tax Agent BenchAgentic US corporate tax research | 30.00%±3.30 | 32.12%±3.37 |
| MedCodeMedical billing code support | 53.22%±2.17 | 48.13%±2.18 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 4.29%±2.44 | 8.57%±3.37 |
| Code Migration v1.1Rewriting programs in new languages | N/A | 38.65%±3.65 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 23.23%±1.34 | 19.70%±2.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 82.72%±3.08 | 78.65%±3.88 |
Benchmarks
Vals Index *
Claude Opus 4.8
N/AGemini 3.8 Flash
0.00%± 1.14
(41/41)Legal Research Bench *
Claude Opus 4.8
0.00%± 3.45
(98/98)Gemini 3.8 Flash
0.00%± 3.39
(98/98)Finance Agent v2.1 *
Claude Opus 4.8
N/AGemini 3.8 Flash
0.00%± 2.04
(44/44)Tax Agent Bench *
Claude Opus 4.8
0.00%± 3.30
(89/89)Gemini 3.8 Flash
0.00%± 3.37
(89/89)MedCode *
Claude Opus 4.8
0.00%± 2.17
(107/107)Gemini 3.8 Flash
0.00%± 2.18
(107/107)Terminal-Bench-Science
Claude Opus 4.8
0.00%± 2.44
(47/47)Gemini 3.8 Flash
0.00%± 3.37
(47/47)Code Migration v1.1 *
Claude Opus 4.8
N/AGemini 3.8 Flash
0.00%± 3.65
(30/30)Terminal-Bench 4.0
Claude Opus 4.8
0.00%± 1.34
(68/68)Gemini 3.8 Flash
0.00%± 2.31
(68/68)Vibe Code Bench v1.1 *
Claude Opus 4.8
0.00%± 3.08
(132/132)Gemini 3.8 Flash
0.00%± 3.88
(132/132)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
Comparison by Industry
Model performance on different sections of the economy.
Legal
63.66%
vs.50.36%
Finance
58.52%
vs.62.11%
Healthcare
69.49%
vs.66.32%
Math
N/A
vs.48.00%
Science
4.29%
vs.35.76%
Academic
89.53%
vs.91.25%
Education
N/A
vs.88.24%
Coding
57.10%
vs.51.47%
Cyber
N/A
vs.27.41%
Social Mobility
68.13%
vs.66.21%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$5.026
Cost / TestVals Index
N/A
vs.$5.026
Input Cost/ 1M Tokens
$5.00
vs.$0.75
Input Cache Write/ 1M Tokens
$6.25
vs.N/A
Input Cache Read/ 1M Tokens
$0.50
vs.$0.075
Output Cost/ 1M Tokens
$25.00
vs.$3.75
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | N/A | 2158.48s |
| Cost (In/Out) | $5 / $25 | $0.75 / $3.75 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 66k |
| Input Modality |