Claude Sonnet 4 vs Nova 2.0 Lite
Wins 4 of 7 areas
Coding · Agents · Facts · Long documents
Wins 3 of 7 areas
Reasoning · Images and charts · Following instructions
Claude Sonnet 4 wins more areas, narrowly.Nova 2.0 Lite is cheaper and better at reasoning.
Scores updated · 22 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.
- CodingWriting and fixing software30Claude Sonnet 43 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 42 of 2 tests
- FactsGetting facts right instead of making them up21Claude Sonnet 42 of 3 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 41 of 1 test
- ReasoningHard problems that need careful thinking01Nova 2.0 Lite1 of 3 tests · 2 ties
- Images and chartsUnderstanding pictures, charts and video01Nova 2.0 Lite1 of 1 test
- Following instructionsDoing exactly what it is asked01Nova 2.0 Lite1 of 1 test
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 Lite 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 Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+62.3points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+20.2points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+14.4points ahead
Where Nova 2.0 Lite pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+16points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.4points ahead
- Harder college exam questions with imagesMMMU-Pro+2points ahead
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4
- Terminal-Bench 2.1Claude Sonnet 4 by 20.236.316.1+20.2
- Terminal-Bench HardClaude Sonnet 4 by 14.431.116.7+14.4
- SciCodeClaude Sonnet 4 by 3.14036.9+3.1
AgentsClaude Sonnet 4
- τ-Bench V3 · BankingClaude Sonnet 4 by 9.916.76.8+9.9
- GDPValClaude Sonnet 4 by 9.79.70+9.7
ReasoningNova 2.0 Lite
- GPQA DiamondNova 2.0 Lite by 3.477.781.1+3.4
- Humanity's Last Examtie10.711.6tie
- CritPttie0.30.3tie
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 62.370.98.6+62.3
- Vectara HHEM hallucination ratelower is betterNova 2.0 Lite by 5.210.35.1+5.2
- AA-Omniscience · AccuracyClaude Sonnet 4 by 3.722.719+3.7
Following instructionsNova 2.0 Lite
- IFBenchNova 2.0 Lite by 1654.770.7+16
Other results8 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 Sonnet 4 by 55.20.2-55+55.2
- Artificial Analysis Coding IndexClaude Sonnet 4 by 14.637.623+14.6
- AA Agentic IndexClaude Sonnet 4 by 14.517.63.1+14.5
- τ²-Bench Telecom (AA run)Nova 2.0 Lite by 8.264.672.8+8.2
- AA IntelligenceClaude Sonnet 4 by 5.518.913.4+5.5
- vectara_factual_consistencyNova 2.0 Lite by 5.289.794.9+5.2
- vectara_avg_summary_lengthClaude Sonnet 4 by 51.7 rating points145.894.1+51.7 rating
- vectara_answer_rateNova 2.0 Lite by 198.699.6+1
Questions people ask
Which is better, Claude Sonnet 4 or Nova 2.0 Lite?
Claude Sonnet 4 wins four of the seven areas where both have results: coding, agents, facts and long documents. Nova 2.0 Lite wins reasoning, images and charts and following instructions, and costs 84% less.
Which is better for coding?
Claude Sonnet 4. It wins 3 of the 3 coding tests both models report; Nova 2.0 Lite wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Nova 2.0 Lite costs $0.30 and $2.50. That makes Nova 2.0 Lite about 84% cheaper for the same work.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.