BenchLeader

LFM2.5-VL-1.6B

Best configuration ranks #599 of 610 on the BenchLeader Index at 34.9 ±7.3.

Blended price
Output speed
First answer
Context
32k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index35
  2. Agents & tools34
  3. Knowledge24
  4. Instruction following37
  5. Multimodal10
  6. Long context25
  7. Composite35

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkdefaultSource
GPQA Diamond (AA)not in index28.9%#496Artificial Analysis
Humanity's Last Exam (AA)not in index5.1%#369Artificial Analysis

Agents & tools

Knowledge

BenchmarkdefaultSource
AA-Omniscience-84.4#470Artificial Analysis

Instruction following

BenchmarkdefaultSource
IFBench33.1%#317Artificial Analysis

Multimodal

BenchmarkdefaultSource
MMMU-Pro26.5%#241Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR0.0%#419Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index4.8#527Artificial Analysis

See also

Data as of 9 Sept 2026. Compare with another model.