Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

Anthropic: Claude Opus 4.7 vs Google: Gemini 3 Flash Preview

Last updated at: 2026-05-10

Metric Claude Opus 4.7 Claude Opus 4.7 none Release: 2026-04-16 Gemini 3 Flash Preview Gemini 3 Flash Preview medium Release: 2025-12-17
Score 8.9 10.0
Rank #5 #1
Reliability 10.0 10.0
Consistency 10.0 10.0
Tests Correct
Attempt pass rate 84.2% 100.0%
Flaky tests 0 0
Total Runs 57 57
Cost per result 3.164 1.722
Total Cost $0.507 $0.328
Input Price $5.000 / 1M $0.500 / 1M
Output Price $25.000 / 1M $3.000 / 1M
Output Tokens 6,329 1,985
Reasoning Tokens 0 102,122
Response Time (avg) 3.04s 11.43s
Response Time (max) 18.27s 74.66s
Response Time (total) 57.79s 217.10s

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 8.3 10.0 75.0% 0 2.12s 522 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 3.88s 330 3,216
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 10.0 10.0 100.0% 0 2.84s 494 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 74.66s 432 48,771
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 9.5 10.0 100.0% 0 18.27s 3,504 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 22.42s 351 10,485
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 10.0 10.0 100.0% 0 2.15s 324 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 5.43s 279 4,893
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 7.7 10.0 66.7% 0 1.19s 78 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 15.27s 12 21,684
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 10.0 10.0 100.0% 0 3.47s 257 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 5.19s 72 1,905
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 10.0 10.0 100.0% 0 1.46s 114 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 4.04s 72 2,709
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 10.0 10.0 100.0% 0 2.58s 661 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 5.48s 192 4,647
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 10.0 10.0 100.0% 0 4.74s 372 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 12.60s 234 1,487
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Opus 4.7 3.0 10.0 0.0% 0 1.46s 3 0
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 5.50s 11 2,325

Quick Compare

Switch Comparison Pair