Models / Step 3.5 Flash
Step 3.5 Flash
Step 3.5 Flash trails most of the field on what it has been measured on; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is Qwen3.5-9B, at $0.11 per million tokens against $0.15.
Results 5 Nov 2026 · 17 results · 3 sources
- Price per million tokens
- $0.10 in · $0.30 out
Typical host on OpenRouter, 5 Nov 2026 · compare prices - Speed
- Not measured
- Intelligence Index
- 16.6
Artificial Analysis - Spring Prompt overall
- Not ranked yet
needs our benchmarks and two groups of results - Developer
- StepFun, based in China
Weights published - Released
- 2 Feb 2026
262,144 tokens of context
Where it stands among the models you could choose
Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 109th of 188Claude Opus 5.5 | – | $0.15 blended, 14th percentilecheapest: Mistral Nemo | – |
| Models priced under $0.25 per million tokens | 9th of 42Claude Haiku 5.5 | – | sets this group | – |
| Models with similar intelligence | sets this group | – | $0.15 blended, 14th percentilecheapest: Qwen3.5-9B | – |
| Models from developers based in China | 47th of 77MiMo-V2.6-Pro | – | $0.15 blended, 9th percentilecheapest: Qwen3.5-9B | – |
| Open-weights models | 48th of 106MiMo-V2.6-Pro | – | $0.15 blended, 21st percentilecheapest: Mistral Nemo | – |
The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.
How good is it, and for what?
Each use case ranks the available models its benchmarks measured, then those priced under $0.25 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.
Product listingsTurning a sparse product feed and photos into listings that can go live
- CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is
- DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
- ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
- tau2-bench: has not measured this model.
- Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
- OpenHands Index: has not measured this model.
- Microsoft STATE-Bench: has not measured this model.
- Artificial Analysis: has not measured this model.
- Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
- APEX-Agents: has not measured this model.
- GDP.pdf: has not measured this model.
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
| Benchmark | Step 3.5 Flash | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 16.6 | 109th of 188 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 21.1% | 98th of 187 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 83.1% | 82nd of 171 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | Step 3.5 Flash | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text: overall · reported | 1,393 | 102nd of 156 | Gemini 4 Argon 1,525 |
| UGI LeaderboardUGI: writing score · reported | 45.9 | 63rd of 126 | Gemini 3.8 Flash 78.6 |
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | Step 3.5 Flash | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text factuality: overall · reported | 1,417 | 88th of 112 | Gemini 4 Argon 1,511 |
- Vectara Hallucination Leaderboard: has not measured this model.
- SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess)
- BulletBench: has not measured this model.
Nearest alternatives
- Cheaper at similar intelligenceQwen3.5-9B$0.11 blended · Intelligence Index 13.3Compare with Step 3.5 Flash →
Against Step 3.5 Flash at $0.15 blended, Intelligence Index 16.6. "Similar intelligence" means within 4 points or better.
Where to run it
1 host on OpenRouter at the standard service tier, with a median of $0.15 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| SiliconFlow | FP8 | $0.10 | $0.30 | $0.15 |
Prices per million tokens from OpenRouter's public endpoint list, checked 5 Nov 2026.
Against the alternatives
The models you would most likely weigh it against: the leaders of the groups above.
Scroll sideways to see every alternative.
| Step 3.5 Flash | Claude Haiku 5.5 most intelligent at under $0.25 per million tokens | Qwen3.5-9B cheapest with similar intelligence | Claude Opus 5.5 most intelligent available today | MiMo-V2.6-Pro most intelligent from China | |
|---|---|---|---|---|---|
| Price per million tokens | $0.15 | $0.20 | $0.11 | $8.00 | $0.54 |
| Tokens a second | – | 240 | 110 | 96 | 43 |
| Intelligence Index | 16.6 | 43.4 | 13.3 | 57.6 | 46.3 |
| Spring Prompt overall | – | 44 | – | 84 | – |
| Rank among available models, by use case | |||||
| Product listings | – | 15th | – | 10th | – |
| Decks from an analysis | – | 14th | – | 4th | – |
| User surveys | – | 4th | – | 3rd | – |
| Marketing planning | – | 26th | – | 7th | – |
| Agents and tool use | pending | 23rd | 109th | 2nd | 19th |
| Professional work | – | – | – | 3rd | – |
| Reasoning and knowledge | 105th of 188 | 22nd | 116th | 1st | 12th |
| Writing | 94th of 173 | – | 114th | 5th | 22nd |
| Sticking to the facts | 118th of 143 | – | – | 3rd | 10th |
| Speed under pressure | – | 19th | – | – | – |
| Side by side → | Side by side → | Side by side → | |||
Shaded figures are better than Step 3.5 Flash's. A dash means no result.
Where it has been measured
9th most intelligent of the 42 models priced under $0.25 per million tokens. Among models available today, in the bottom quarter for sticking to the facts. Results for agents and tool use are pending: those sources last updated before this model was released.
Artificial Analysis lists it but has not published a speed for it yet
- Arena (formerly LMArena)7 results
- Artificial Analysis7 results
- UGI Leaderboard3 results
- Berkeley Function Calling Leaderboard (BFCL) V4Pending: latest results 16 Dec 2025
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- APEX-AgentsNot measured
- GDP.pdfNot measured
- Microsoft STATE-BenchNot measured
- OpenHands IndexNot measured
- Remote Labor IndexNot measured
- SimpleQA Verified (Epoch AI)Not measured
- tau2-benchNot measured
- Vectara Hallucination LeaderboardNot measured
- Vending-Bench 2Not measured
Every result
17 published results from 3 sources, each in the source's own units, with the configuration that produced it.
Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Arena Text factuality: overallArena rating, higher is better | 1,417 1,414–1,420 |
138 of 182 | Step 3.5 Flash | 2 Oct 2026 |
| Arena Text: business, management and financeArena rating, higher is better | 1,391 1,384–1,397 |
170 of 406 | Step 3.5 Flash | 2 Oct 2026 |
| Arena Text: creative writingArena rating, higher is better | 1,345 1,339–1,352 |
180 of 411 | Step 3.5 Flash | 2 Oct 2026 |
| Arena Text: expert promptsArena rating, higher is better | 1,429 1,420–1,437 |
143 of 363 | Step 3.5 Flash | 2 Oct 2026 |
| Arena Text: instruction followingArena rating, higher is better | 1,384 1,379–1,389 |
166 of 413 | Step 3.5 Flash | 2 Oct 2026 |
| Arena Text: overallArena rating, higher is better | 1,393 1,390–1,397 |
169 of 413 | Step 3.5 Flash | 2 Oct 2026 |
| Arena Text: writing, literature and languageArena rating, higher is better | 1,366 1,360–1,372 |
176 of 412 | Step 3.5 Flash | 2 Oct 2026 |
Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
Artificial Analysis · reported by Artificial Analysis · 7 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 16.6 | 240 of 413 | Step 3.5 Flash | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 83.1% | 148 of 360 | Step 3.5 Flash | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 21.1% | 188 of 411 | Step 3.5 Flash | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 64.6% | 90 of 288 | Step 3.5 Flash | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 50.0% | 271 of 399 | Step 3.5 Flash | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 27.3% | 117 of 282 | Step 3.5 Flash | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 94.4% | 27 of 286 | Step 3.5 Flash | 20 Oct 2026 |
Not shown: Not business work, and a blend: read the parts for any one task.
UGI Leaderboard · reported by UGI Leaderboard · 3 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| UGI: requested-length error% off the requested word count, lower is better | 42.0% | 304 of 379 | Step 3.5 Flash | 11 Feb 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.37 | 85 of 379 | Step 3.5 Flash | 11 Feb 2026 |
| UGI: writing scorescore out of 100, higher is better | 45.9 | 182 of 379 | Step 3.5 Flash | 11 Feb 2026 |
Not shown: Not other format limits such as character counts or bullet counts.
Test Step 3.5 Flash on your own prompt.
Benchmarks aren't your task. Run it next to cheaper and newer models on your prompt, with every answer checked and costed.