Navigate
AI BENCHY
Advertise here

Anthropic: Claude Fable 5 vs OpenAI: GPT-5.2

Claude Fable 5 (medium) leads on average score with 8.6 vs 8.4. GPT-5.2 (medium) has the lower benchmark cost at $0.951 vs $3.478. Claude Fable 5 (medium) is faster at 17.20s vs 22.62s, with pass rates of 78.8% vs 72.7%.

Recommended modelGPT-5.2 (medium)Its score stays close to the best score here (8.4 vs 8.6), while costing about 3.7x less than Claude Fable 5 (medium).

Last updated at: 2026-07-25

Metric Claude Fable 5 Claude Fable 5 medium Release: 2026-06-10 GPT-5.2 GPT-5.2 medium Release: 2025-12-11
Score 8.6 8.4
Rank #22 #27
Reliability 10.0 10.0
Consistency 9.6 8.5
Tests Correct
Attempt pass rate 78.8% 72.7%
Flaky tests 1 4
Total Runs 66 66
Cost per result 20.459 6.791
Total Cost $3.478 $0.951
Input Price $10.000 / 1M $1.750 / 1M
Output Price $50.000 / 1M $14.000 / 1M
Total Input Tokens 89,643 105,004
Output Tokens 41,360 9,914
Reasoning Tokens 10,269 44,868
Response Time (avg) 17.20s 22.62s
Response Time (max) 80.80s 102.93s
Response Time (total) 378.41s 339.28s

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#22 Claude Fable 5

medium
Cost
$0.606
Time
156.7s
Tokens
12,264 tok

#27 GPT-5.2

medium
Cost
$0.047
Time
49.2s
Tokens
3,396 tok

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

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Fable 5 10.0 10.0 100.0% 0 15.59s 10,590 7,383 1,318
GPT-5.2 10.0 10.0 100.0% 0 22.73s 7,302 511 11,912

Quick Compare

Switch Comparison Pair