Celeris-1 vs LongCat-2.0
Wins 0 of 5 areas
—
Wins 5 of 5 areas
Coding · Agents · Reasoning · Facts · Long documents
LongCat-2.0 is the stronger all-rounder.Celeris-1 is cheaper.
Scores updated · 14 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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 thinking03LongCat-2.03 of 3 tests
- AgentsCarrying out multi-step tasks on its own02LongCat-2.02 of 3 tests · 1 tie
- CodingWriting and fixing software02LongCat-2.02 of 2 tests
- FactsGetting facts right instead of making them up02LongCat-2.02 of 2 tests
- Long documentsFinding answers in very long texts01LongCat-2.01 of 1 test
Long documents rests on a single test.
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.
Celeris-1 costs 40% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where LongCat-2.0 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+39points ahead
- Reasons across sets of long documentsAA-LCR+27points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+26.9points ahead
Where Celeris-1 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLongCat-2.0
- Terminal-Bench 2.1LongCat-2.0 by 3911.250.2+39
- SciCodeLongCat-2.0 by 14.721.636.3+14.7
AgentsLongCat-2.0
- GDPValLongCat-2.0 by 18.6018.6+18.6
- τ-Bench V3 · BankingLongCat-2.0 by 9.33.913.2+9.3
- Terminal-Bench 4.0tie00tie
ReasoningLongCat-2.0
- Humanity's Last ExamLongCat-2.0 by 26.96.833.7+26.9
- GPQA DiamondLongCat-2.0 by 14.963.178+14.9
- CritPtLongCat-2.0 by 2.602.6+2.6
FactsLongCat-2.0
- AA-Omniscience · AccuracyLongCat-2.0 by 18.61129.6+18.6
- AA-Omniscience · Non-hallucinationLongCat-2.0 by 17.47.224.6+17.4
Other results3 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-OmniscienceLongCat-2.0 by 48.2-71.6-23.4+48.2
- Artificial Analysis Coding IndexLongCat-2.0 by 30.914.445.3+30.9
- AA IntelligenceLongCat-2.0 by 12.86.319.1+12.8
Questions people ask
Which is better, Celeris-1 or LongCat-2.0?
LongCat-2.0 wins all five areas where both have results: coding, agents, reasoning, facts and long documents. Celeris-1 wins none, but costs 40% less.
Which is better for coding?
LongCat-2.0. It wins 2 of the 2 coding tests both models report; Celeris-1 wins none.
Which is cheaper?
Celeris-1 costs $0.20 per million input tokens and $0.70 per million output tokens; LongCat-2.0 costs $0.30 and $1.20. That makes Celeris-1 about 40% cheaper for the same work.
How do you compare the two?
We use the 14 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 3 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.