Step 3.7 Flash
Context
n/a
Max output
n/a
Serving providers
0
Cheapest input
n/a /1M
Benchmarks
independent evaluations · source: Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
463 t/s
tokens / second
Time to first token
3.06s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| APEX Agents | 15% | default | — | |
| CritPt | 2% | default | — | |
| EvalComputeProxy | 3862.3 | default | — | |
| GDPval | 1017.0 | default | — | |
| GPQA Diamond | 81% | default | — | |
| Humanity's Last Exam | 20% | default | — | |
| IFBench | 67% | default | — | |
| IT-Bench SRE | 30% | default | — | |
| Long-Context Reasoning | 64% | default | — | |
| MMMU-Pro | 75% | default | — | |
| Omniscience | -37.5 | default | — | |
| SciCode | 40% | default | — | |
| SWE-bench Pro | 56% | default | — | |
| TerminalBench Hard | 36% | default | — | |
| TerminalBench v2.1 | 39% | default | — | |
| τ-bench Banking | 11% | default | — | |
| τ²-bench | 99% | default | — |
Pricing by serving provider
availabilityNo public price yet. Not offered on-demand at any tracked provider.
Price history
input + output $/1M since we started tracking Input Output
Price history is accruing. We record a point each day a price changes; the full backfill lands shortly.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI