BenchLeader
RekaAuto-detected

Reka Flash

Best configuration ranks #446 of 610 on the BenchLeader Index at 43.1 ±3.3. Last measured 2 Sept 2026.

Blended price
$0.350/M
$0.200 in · $0.800 out
Output speed
First answer
Context
128k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index43
  2. Reasoning41
  3. Coding41
  4. Human preference43
  5. Multimodal32
  6. Composite37

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
LMArena Hard Prompts1267#259LMArena

Coding

BenchmarkdefaultSource
LMArena Coding1291#257LMArena

Human preference

BenchmarkdefaultSource
LMArena Text1272#254LMArena

Multimodal

BenchmarkdefaultSource
MMMU (validation)53.3%#38MMMU

Composite

BenchmarkdefaultSource
AA Intelligence Index6.4#444Artificial Analysis

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0003
Summarise a 30-page report12,000 / 600$0.0029
Code edit6,000 / 1,500$0.0024
Agentic coding session60,000 / 4,000$0.015
Structured extraction2,000 / 200$0.0006

See also

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