Claude 3.7 Sonnet vs Nova 2.0 Omni Reasoning Medium
Wins 4 of 7 areas
Coding · Agents · Reasoning · Facts
Wins 3 of 7 areas
Images and charts · Long documents · Following instructions
Claude 3.7 Sonnet wins more areas, narrowly.Nova 2.0 Omni Reasoning Medium is cheaper and better at images and charts.
Scores updated · 16 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking20Claude 3.7 Sonnet2 of 3 tests · 1 tie
- CodingWriting and fixing software20Claude 3.7 Sonnet2 of 2 tests
- FactsGetting facts right instead of making them up20Claude 3.7 Sonnet2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Claude 3.7 Sonnet1 of 1 test
- Images and chartsUnderstanding pictures, charts and video01Nova 2.0 Omni Reasoning Medium1 of 1 test
- Long documentsFinding answers in very long texts01Nova 2.0 Omni Reasoning Medium1 of 1 test
- Following instructionsDoing exactly what it is asked01Nova 2.0 Omni Reasoning Medium1 of 1 test
Agents, images and charts, long documents and following instructions rest on a single test each.
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.
Nova 2.0 Omni Reasoning Medium costs 84% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude 3.7 Sonnet pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+53.3points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+16.7points ahead
- Real work tasks from 44 professionsGDPVal+13.3points ahead
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude 3.7 Sonnet
- Terminal-Bench HardClaude 3.7 Sonnet by 16.721.24.5+16.7
- SciCodeClaude 3.7 Sonnet by 4.140.336.2+4.1
ReasoningClaude 3.7 Sonnet
- Humanity's Last ExamClaude 3.7 Sonnet by 2.79.77+2.7
- GPQA DiamondClaude 3.7 Sonnet by 1.277.276+1.2
- CritPttie0.90tie
FactsClaude 3.7 Sonnet
- AA-Omniscience · Non-hallucinationClaude 3.7 Sonnet by 53.3606.7+53.3
- AA-Omniscience · AccuracyClaude 3.7 Sonnet by 10.32817.7+10.3
Images and chartsNova 2.0 Omni Reasoning Medium
- MMMU-ProNova 2.0 Omni Reasoning Medium by 1.860.161.9+1.8
Long documentsNova 2.0 Omni Reasoning Medium
- AA-LCRNova 2.0 Omni Reasoning Medium by 851.759.7+8
Following instructionsNova 2.0 Omni Reasoning Medium
- IFBenchNova 2.0 Omni Reasoning Medium by 17.948.366.2+17.9
Other results5 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- AA-OmniscienceClaude 3.7 Sonnet by 58.4-0.7-59.1+58.4
- τ²-Bench Telecom (AA run)Nova 2.0 Omni Reasoning Medium by 25.754.780.4+25.7
- Artificial Analysis Coding IndexClaude 3.7 Sonnet by 21.336.415.1+21.3
- AA IntelligenceClaude 3.7 Sonnet by 4.117.713.6+4.1
- AA Agentic IndexNova 2.0 Omni Reasoning Medium by 1.23738.2+1.2
Questions people ask
Which is better, Claude 3.7 Sonnet or Nova 2.0 Omni Reasoning Medium?
Claude 3.7 Sonnet wins four of the seven areas where both have results: coding, agents, reasoning and facts. Nova 2.0 Omni Reasoning Medium wins images and charts, long documents and following instructions, and costs 84% less.
Which is better for coding?
Claude 3.7 Sonnet. It wins 2 of the 2 coding tests both models report; Nova 2.0 Omni Reasoning Medium wins none.
Which is cheaper?
Claude 3.7 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens; Nova 2.0 Omni Reasoning Medium costs $0.30 and $2.50. That makes Nova 2.0 Omni Reasoning Medium about 84% cheaper for the same work.
How do you compare the two?
We use the 16 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.