BenchLeader

Reka Flash

Reka Flash is a Reka proprietary model, released 4 Oct 2024. Its best configuration ranks #599 of 785 on the BenchLeader Index at 42.4 ±2.2, in the lower half. The ± is the point: 277 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in human preference (42) and lowest in multimodal (34). At $0.350 per million tokens blended it is cheaper than most ranked models. Last measured 22 Oct 2026.

Blended price
$0.350/M
$0.200 in · $0.800 out
Output speed
–
First answer
–
Context
128k
Full answer
–
Cost per run
–
Released
4 Oct 2024
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index42
  2. Reasoning40
  3. Coding40
  4. Maths39
  5. Human preference42
  6. Multimodal34
  7. Composite37

Versions

Reka has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Reka Flash 310 Mar 202538.9#702
Reka Flashthis page4 Oct 202442.4#599

How its index has moved

9 Sept 2026 to 21 Oct 2026
404345

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. 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

Benchmarknot statedSourceTrend
Arena Hard Prompts1268#283Arena (LMArena)

Coding

Benchmarknot statedSourceTrend
Arena Coding1292#282Arena (LMArena)

Maths

Benchmarknot statedSourceTrend
Arena Maths1233#275Arena (LMArena)

Instruction following

Benchmarknot statedSourceTrend
Arena Instruction Followingnot in index1250#280Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1273#278Arena (LMArena)
Arena Creative Writingnot in index1243#269Arena (LMArena)
Arena Multi-turnnot in index1238#283Arena (LMArena)
Arena Longer Queriesnot in index1266#282Arena (LMArena)

Multimodal

Benchmarknot statedSourceTrend
MMMU (validation)53.3%#41MMMU

Composite

Benchmarknot statedSourceTrend
AA Intelligence Index v4.3.26.4#529Artificial 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––
Summarize 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––

More from Reka

New this month

See also

Questions people ask

What are Reka Flash's benchmark scores?
As of 25 Oct 2026, Reka Flash scores 42.4 ±2.2 on the BenchLeader Index, strongest in human preference (42) and weakest in multimodal (34). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
How does Reka Flash rank?
Reka Flash is #599 of 785 ranked configurations on 25 Oct 2026. 277 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
How much does Reka Flash cost per 1M tokens?
As of 25 Oct 2026, Reka Flash costs $0.200 per 1M input tokens and $0.800 per 1M output tokens, $0.350 blended (three input tokens per output token).
When was Reka Flash released?
Reka released Reka Flash on 4 Oct 2024.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Reka Flash: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/reka-flash.