Scores updated · 11 tests both models report · How we compare
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Claude 3.5 Sonnet$3.00 to read · $15.00 to writePrice from Artificial Analysis
Qwen2.5 Instruct Turbo (7B)No current price is tracked.
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results11 tests
- AIR-Bench 2024Claude 3.5 Sonnet by 38.985.947+38.9
- HarmBenchClaude 3.5 Sonnet by 30.498.167.7+30.4
- naturalquestions_closedbookClaude 3.5 Sonnet by 29.750.220.5+29.7
- MMLUClaude 3.5 Sonnet by 22.988.765.8+22.9
- GSM8KClaude 3.5 Sonnet by 13.496.483+13.4
- OpenBookQAClaude 3.5 Sonnet by 1197.286.2+11
- bbqClaude 3.5 Sonnet by 4.394.990.6+4.3
- simple_safety_testsClaude 3.5 Sonnet by 410096+4
- anthropic_red_teamClaude 3.5 Sonnet by 1.399.898.5+1.3
- XSTestQwen2.5 Instruct Turbo (7B) by 195.696.6+1
- NarrativeQAtie74.674.2tie
Questions people ask
How do you compare the two?
We use the 11 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.