Navigate
AI BENCHY
Advertise here

Anthropic: Claude Opus 4.8 vs Qwen: Qwen3.5-122B-A10B

Claude Opus 4.8 leads on average score with 7.3 vs 7.1. Qwen3.5-122B-A10B (medium) has the lower benchmark cost at $1.046 vs $1.166. Claude Opus 4.8 is faster at 4.91s vs 64.16s, with pass rates of 63.6% vs 71.2%.

Recommended modelClaude Opus 4.8It has the best score here (7.3), while responding about 13.1x faster than Qwen3.5-122B-A10B (medium).

Last updated at: 2026-07-17

Metric Claude Opus 4.8 Claude Opus 4.8 none Release: 2026-05-28 Qwen3.5-122B-A10B Qwen3.5-122B-A10B medium Release: 2026-02-24
Score 7.3 7.1
Rank #63 #69
Reliability 10.0 10.0
Consistency 9.2 8.5
Tests Correct
Attempt pass rate 63.6% 71.2%
Flaky tests 2 4
Total Runs 66 66
Cost per result 8.969 8.509
Total Cost $1.166 $1.046
Input Price $5.000 / 1M $0.260 / 1M
Output Price $25.000 / 1M $2.080 / 1M
Total Input Tokens 149,206 124,771
Output Tokens 16,797 44,077
Reasoning Tokens 0 443,141
Response Time (avg) 4.91s 64.16s
Response Time (max) 35.03s 519.30s
Response Time (total) 108.03s 1411.60s

Hamster playing table tennis

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

#63 Claude Opus 4.8

none
Cost
$0.053
Time
22.0s
Tokens
2,253 tok

#69 Qwen3.5-122B-A10B

medium
Cost
$0.019
Time
48.7s
Tokens
6,034 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 Opus 4.8 5.5 10.0 33.3% 0 3.29s 10,590 1,332 0
Qwen3.5-122B-A10B 6.0 7.2 55.6% 1 114.48s 7,630 8,057 82,578

Quick Compare

Switch Comparison Pair