BenchLeader
TII UAEOpen weightsReasoning modelAuto-detected

Falcon-H1R-7B

Best configuration ranks #444 of 610 on the BenchLeader Index at 43.1 ±7.4.

Blended price
Output speed
First answer
Context
256k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index43
  2. Agents & tools36
  3. Knowledge35
  4. Instruction following55
  5. Long context30
  6. Composite39

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 index66.1%#320Artificial Analysis
Humanity's Last Exam (AA)not in index11.0%#240Artificial Analysis

Agents & tools

Knowledge

BenchmarkdefaultSource
AA-Omniscience-61.3#396Artificial Analysis

Instruction following

BenchmarkdefaultSource
IFBench54.4%#150Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR11.0%#392Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index7.8#377Artificial Analysis

See also

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