Claude 3 Haiku vs Ling-flash-2.0
Wins 3 of 6 areas
Facts · Long documents · Following instructions
Wins 2 of 6 areas
Coding · Reasoning
Claude 3 Haiku wins more areas, narrowly.Ling-flash-2.0 is cheaper and better at reasoning.
Scores updated · 15 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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.
- FactsGetting facts right instead of making them up20Claude 3 Haiku2 of 2 tests
- Long documentsFinding answers in very long texts10Claude 3 Haiku1 of 1 test
- Following instructionsDoing exactly what it is asked10Claude 3 Haiku1 of 1 test
- ReasoningHard problems that need careful thinking02Ling-flash-2.02 of 3 tests · 1 tie
- CodingWriting and fixing software02Ling-flash-2.02 of 2 tests
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
Agents, 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.
Ling-flash-2.0 costs 53% 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 Haiku pulls ahead
- Reasons across sets of long documentsAA-LCR+10points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.5points ahead
Where Ling-flash-2.0 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+28.3points ahead
- Code for real scientific research problemsSciCode+10.3points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+9.8points ahead
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLing-flash-2.0
- SciCodeLing-flash-2.0 by 10.318.628.9+10.3
- Terminal-Bench HardLing-flash-2.0 by 9.80.810.6+9.8
ReasoningLing-flash-2.0
- GPQA DiamondLing-flash-2.0 by 28.337.465.7+28.3
- Humanity's Last ExamLing-flash-2.0 by 2.14.16.2+2.1
- CritPttie00tie
FactsClaude 3 Haiku
- AA-Omniscience · Non-hallucinationClaude 3 Haiku by 919.510.5+9
- AA-Omniscience · AccuracyClaude 3 Haiku by 3.517.614.1+3.5
Following instructionsClaude 3 Haiku
- IFBenchClaude 3 Haiku by 1.736.134.4+1.7
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 Haiku by 14.1-48.6-62.7+14.1
- Artificial Analysis Coding IndexLing-flash-2.0 by 106.716.7+10
- AA IntelligenceLing-flash-2.0 by 2.25.67.8+2.2
- AA Agentic IndexLing-flash-2.0 by 1.378.3+1.3
- τ²-Bench Telecom (AA run)tie21.120.8tie
Questions people ask
Which is better, Claude 3 Haiku or Ling-flash-2.0?
Claude 3 Haiku wins three of the six areas where both have results: facts, long documents and following instructions. Ling-flash-2.0 wins coding and reasoning, and costs 53% less. They are level on agents.
Which is better for coding?
Ling-flash-2.0. It wins 2 of the 2 coding tests both models report; Claude 3 Haiku wins none.
Which is cheaper?
Claude 3 Haiku costs $0.25 per million input tokens and $1.25 per million output tokens; Ling-flash-2.0 costs $0.14 and $0.57. That makes Ling-flash-2.0 about 53% cheaper for the same work.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 10 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.