Reka Flash 3
- Input
- $0.20/M tok
- Output
- $0.80/M tok
- Blended
- $0.35/M tok · 3:1
- Speed
- 94tok/s
- Context
- 128Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Reka Flash 3. Price = AA median host price.
Rankings
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.
- Hardware
- 1× B200 180GB
- BF16 weights
- Throughput
- ~5,602 tok/s
- many requests batched
- Price
- $0.16–1.47 /M tok
- busy → light use
- On your own machine
- RTX 5090 32GB (int4, ~120 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- BF16 weights (20.9B params) + 25% KV-cache headroom ≈ 52 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~5,602 output tok/s aggregate at batch 160 (bandwidth-bound)
- Blended 3:1 input:output; prefill ~25,434 tok/s
- Low = 75% utilization at the low GPU price; high = 20% at the high price
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Writing & chat
IFBenchVerified
#115 of 13930.4%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #115Llama 3.2 Instruct 11B (Vision)30.4%
- #115Reka Flash 330.4%
- #117Nova Micro29.4%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#52 of 57 (estimated)~1298 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #51gpt-oss-20b1299
- ~#52Reka Flash 3Estimated1298
- #52Olmo 3.1 32B Instruct1294
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#51 of 57 (estimated)~1324 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #50Llama 4 Maverick1327
- ~#51Reka Flash 3Estimated1324
- #51Molmo2-8BFew votes1322
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#22 of 26 (estimated)~1425 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #21Gemini 3.1 Pro1491
- ~#22Reka Flash 3Estimated1425
- #22Mistral Large 31412
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#150 of 19252.9%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #149Devstral Small 253.2%
- #150Reka Flash 352.9%
- #151Command A52.7%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#179 of 1984.4%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #179Jamba 1.7 Mini4.4%
- #179Reka Flash 34.4%
- #181Ministral 3 8B4.3%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#24 of 34 (estimated)~37.9%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #23Mistral Large 338.0%
- ~#24Reka Flash 3Estimated37.9%
- #24Devstral 236.7%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#102 of 103 (estimated)~4.1
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #100NVIDIA Nemotron 3 Nano 4B4.8
- ~#102Reka Flash 3Estimated4.1
- #102K2 Horizon 0.9B3.0
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#110 of 1190.0%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #110Phi-40.0%
- #110Reka Flash 30.0%
- #110Ring-flash-2.00.0%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#13 of 15 (estimated)~51.4%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #12Nemotron 3.5 Super VL NVFP452.3%
- ~#13Reka Flash 3Estimated51.4%
- #13Nemotron 3.5 Super VL51.1%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~33.5%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21Reka Flash 3Estimated33.5%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#61 of 92 (estimated)~636 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #60MiniCPM5-2B694
- ~#61Reka Flash 3Estimated636
- #61Nemotron 3.5 Lightning624
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#79 of 85 (estimated)~0.2%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #77Granite 4.2 3B0.4%
- ~#79Reka Flash 3Estimated0.2%
- #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~last of 91 (estimated)below measured range (<3.3%)
No published score — estimated from related benchmarks