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 Opus$15.00 to read · $75.00 to writePrice from Artificial Analysis
Mistral Instruct V0.3 (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
- HarmBenchClaude 3 Opus by 6397.434.4+63
- AIR-Bench 2024Claude 3 Opus by 51.884.432.5+51.8
- GSM8KClaude 3 Opus by 41.29553.8+41.2
- NarrativeQAMistral Instruct V0.3 (7B) by 36.535.171.6+36.5
- MMLUClaude 3 Opus by 35.886.851+35.8
- bbqClaude 3 Opus by 27.29466.8+27.2
- simple_safety_testsClaude 3 Opus by 1910081+19
- naturalquestions_closedbookClaude 3 Opus by 18.84425.3+18.8
- OpenBookQAClaude 3 Opus by 16.695.679+16.6
- anthropic_red_teamClaude 3 Opus by 9.799.890.1+9.7
- XSTesttie92.592.6tie
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.