Claude Haiku 4.5 vs ling-2-6-1t
Wins 1 of 6 areas
Long documents
Wins 2 of 6 areas
Agents · Following instructions
ling-2-6-1t wins more areas, narrowly.Claude Haiku 4.5 is better at long documents.
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.
- AgentsCarrying out multi-step tasks on its own01ling-2-6-1t1 of 1 test
- Following instructionsDoing exactly what it is asked01ling-2-6-1t1 of 1 test
- Long documentsFinding answers in very long texts10Claude Haiku 4.51 of 1 test
- CodingWriting and fixing software11Even1 each
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
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-2-6-1t 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 ling-2-6-1t pulls ahead
- Real work tasks from 44 professionsGDPVal+15.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.9points ahead
Where Claude Haiku 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+65.5points ahead
- Reasons across sets of long documentsAA-LCR+32.6points ahead
- Code for real scientific research problemsSciCode+5.2points 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.
CodingEven
- SciCodeClaude Haiku 4.5 by 5.242.237+5.2
- Terminal-Bench Hardling-2-6-1t by 3.827.331.1+3.8
ReasoningEven
- GPQA Diamondling-2-6-1t by 867.275.2+8
- Humanity's Last ExamClaude Haiku 4.5 by 1.710.48.7+1.7
- CritPttie00.3tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude Haiku 4.5 by 65.572.77.2+65.5
- AA-Omniscience · Accuracyling-2-6-1t by 3.91821.9+3.9
Long documentsClaude Haiku 4.5
- AA-LCRClaude Haiku 4.5 by 32.674.341.7+32.6
Following instructionsling-2-6-1t
- IFBenchling-2-6-1t by 2.654.356.9+2.6
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 Haiku 4.5 by 46.2-4.4-50.6+46.2
- AA Agentic Indexling-2-6-1t by 37.910.348.2+37.9
- τ²-Bench Telecom (AA run)ling-2-6-1t by 35.154.789.8+35.1
- Artificial Analysis Coding IndexClaude Haiku 4.5 by 10.843.933.1+10.8
- AA Intelligencetie16.917tie
Questions people ask
Which is better, Claude Haiku 4.5 or ling-2-6-1t?
ling-2-6-1t wins two of the six areas where both have results: agents and following instructions. Claude Haiku 4.5 wins long documents. They are level on coding, reasoning and facts.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
Which is cheaper?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; ling-2-6-1t costs $0.30 and $2.50. That makes ling-2-6-1t 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.