Beam 1.0 vs Kimi K2.5
Wins 6 of 6 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
Wins 0 of 6 areas
—
Beam 1.0 is the stronger all-rounder.
Scores updated · 18 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.
- CodingWriting and fixing software40Beam 1.04 of 5 tests · 1 tie
- ReasoningHard problems that need careful thinking40Beam 1.04 of 4 tests
- AgentsCarrying out multi-step tasks on its own20Beam 1.02 of 2 tests
- MathCompetition and research-level math10Beam 1.01 of 1 test
- Long documentsFinding answers in very long texts10Beam 1.01 of 1 test
- Following instructionsDoing exactly what it is asked10Beam 1.01 of 1 test
Math, 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Beam 1.0 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+34.4points ahead
- Multi-step tasks using many real software toolsMCP Atlas+17points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+15.4points ahead
Where Kimi K2.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingBeam 1.0
- Terminal-Bench 2.1Beam 1.0 by 34.480.145.7+34.4
- SWE-bench ProBeam 1.0 by 15.466.150.7+15.4
- SWE-bench MultilingualBeam 1.0 by 5.378.373+5.3
- SWE-bench VerifiedBeam 1.0 by 4.881.676.8+4.8
- SciCodetie49.249tie
AgentsBeam 1.0
- MCP AtlasBeam 1.0 by 1780.863.8+17
- BrowseCompBeam 1.0 by 1.976.874.9+1.9
ReasoningBeam 1.0
- CritPtBeam 1.0 by 13.216.33.1+13.2
- ARC-AGI-2Beam 1.0 by 11.723.511.8+11.7
- Humanity's Last ExamBeam 1.0 by 5.33630.7+5.3
- GPQA DiamondBeam 1.0 by 2.790.687.9+2.7
Other results4 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.
- τ³-Bench BankingBeam 1.0 by 21.936.114.2+21.9
- ARC-AGI-1Beam 1.0 by 8.77465.3+8.7
- DeepSearchQA (F1)Beam 1.0 by 3.480.577.1+3.4
- HLE (with tools)tie51.150.2tie
Questions people ask
Which is better, Beam 1.0 or Kimi K2.5?
Beam 1.0 wins all six areas where both have results: coding, agents, reasoning, math, long documents and following instructions. Kimi K2.5 wins none.
Which is better for coding?
Beam 1.0. It wins 4 of the 5 coding tests both models report; Kimi K2.5 wins none, and 1 is a tie.
How do you compare the two?
We use the 18 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 4 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.