Ember-1 vs Step 3.5 Flash
Updated October 21, 2026. No benchmark has tested both models yet. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
- Coding
- 52.6
- Overall
- No data
- Output $/M
- $15.00
- Coding
- No data
- Overall
- 17.0
- Output $/M
- $0.30
Decision reading
Only Ember-1 has a coding score, 52.6 on the Vibe Coding Index; Step 3.5 Flash has none, so the two cannot be ranked on coding.
Step 3.5 Flash has the edge where output tokens cost 50.0x less.
No benchmark has tested both yet. Ember-1 has results on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Code migration (Vals AI); Step 3.5 Flash on Terminal-Bench Hard (Artificial Analysis run), LMArena Text: coding and LMArena Text: software and IT. Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Ember-1 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Step 3.5 Flash has a AA Intelligence Index result, 17.0.
Directional only
Long documents
Listed context window
Ember-1
Ember-1 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Step 3.5 Flash
Ember-1 $0.011, Step 3.5 Flash $0.0003 per turn.
List prices
At a glance
- Coding index
- Ember-1 52.6 from 2 benchmarks, Step 3.5 Flash not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Ember-1 $15.00 against Step 3.5 Flash $0.30 per million output tokens, 50.0x apart.
- Context window
- Ember-1 takes 1.05M tokens, Step 3.5 Flash 262K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index8 boards measured
| Benchmark | Ember-1 | Step 3.5 Flash | Leader |
|---|---|---|---|
| Terminal-Bench 4 (Vals AI) | 20.7% | Not measured | Only Ember-1 measured |
| Vibe Code Bench (Vals AI) | 83.9% | Not measured | Only Ember-1 measured |
| Code migration (Vals AI) | 32.5% | Not measured | Only Ember-1 measured |
| IOI (Vals AI) | 46.3% | Not measured | Only Ember-1 measured |
| CyberBench (Vals AI) | 69.5% | Not measured | Only Ember-1 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 32.6% | Only Step 3.5 Flash measured |
| LMArena Text: coding | Not measured | 1436 | Only Step 3.5 Flash measured |
| LMArena Text: software and IT | Not measured | 1434 | Only Step 3.5 Flash measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Ember-1 | Step 3.5 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 17.0 | Only Step 3.5 Flash measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index8 boards measured
| Benchmark | Ember-1 | Step 3.5 Flash | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | 51.8% | Not measured | Only Ember-1 measured |
| Tax Agent Bench (Vals AI) | 31.1% | Not measured | Only Ember-1 measured |
| Legal Research Bench (Vals AI) | 44.7% | Not measured | Only Ember-1 measured |
| Excel Modeling Benchmark (Vals AI) | 63.4% | Not measured | Only Ember-1 measured |
| BioMysteryBench (Vals AI) | 67.0% | Not measured | Only Ember-1 measured |
| Terminal-Bench-Science (Vals AI) | 5.7% | Not measured | Only Ember-1 measured |
| Vals Science Index | 31.8% | Not measured | Only Ember-1 measured |
| τ²-Bench Telecom | Not measured | 94.4% | Only Step 3.5 Flash measured |
| Neither model has a result on the other 31 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Ember-1 | Step 3.5 Flash | Leader |
|---|---|---|---|
| MysteryMechanism (Vals AI) | 22.5% | Not measured | Only Ember-1 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 83.1% | Only Step 3.5 Flash measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 24.5% | Only Step 3.5 Flash measured |
| LMArena Text: hard prompts | Not measured | 1411 | Only Step 3.5 Flash measured |
| LMArena Text: expert | Not measured | 1421 | Only Step 3.5 Flash measured |
| LMArena Text: hard prompts in English | Not measured | 1421 | Only Step 3.5 Flash measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Ember-1 | Step 3.5 Flash | Leader |
|---|---|---|---|
| LMArena Text: math | Not measured | 1408 | Only Step 3.5 Flash measured |
| LMArena Text: mathematical work | Not measured | 1421 | Only Step 3.5 Flash measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Ember-1 | Step 3.5 Flash | Leader |
|---|---|---|---|
| LMArena Text: science | Not measured | 1415 | Only Step 3.5 Flash measured |
| LMArena Text: medicine and healthcare | Not measured | 1408 | Only Step 3.5 Flash measured |
| LMArena Text: legal and government | Not measured | 1408 | Only Step 3.5 Flash measured |
| LMArena Text: business and finance | Not measured | 1394 | Only Step 3.5 Flash measured |
| Neither model has a result on the other 13 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index20 boards measured
| Benchmark | Ember-1 | Step 3.5 Flash | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 66.2% | Not measured | Only Ember-1 measured |
| IFBench | Not measured | 66.5% | Only Step 3.5 Flash measured |
| Long context reasoning (AA-LCR) | Not measured | 63.0% | Only Step 3.5 Flash measured |
| LMArena Text | Not measured | 1403 | Only Step 3.5 Flash measured |
| LMArena Text: instruction following | Not measured | 1385 | Only Step 3.5 Flash measured |
| LMArena Text: creative writing | Not measured | 1357 | Only Step 3.5 Flash measured |
| LMArena Text: English | Not measured | 1417 | Only Step 3.5 Flash measured |
| LMArena Text: non-English | Not measured | 1385 | Only Step 3.5 Flash measured |
| LMArena Text: Chinese | Not measured | 1446 | Only Step 3.5 Flash measured |
| LMArena Text: German | Not measured | 1405 | Only Step 3.5 Flash measured |
| LMArena Text: Japanese | Not measured | 1353 | Only Step 3.5 Flash measured |
| LMArena Text: Korean | Not measured | 1351 | Only Step 3.5 Flash measured |
| LMArena Text: French | Not measured | 1421 | Only Step 3.5 Flash measured |
| LMArena Text: Spanish | Not measured | 1419 | Only Step 3.5 Flash measured |
| LMArena Text: Russian | Not measured | 1385 | Only Step 3.5 Flash measured |
| LMArena Text: Polish | Not measured | 1389 | Only Step 3.5 Flash measured |
| LMArena Text: multi-turn | Not measured | 1404 | Only Step 3.5 Flash measured |
| LMArena Text: longer queries | Not measured | 1402 | Only Step 3.5 Flash measured |
| LMArena Text: writing and language | Not measured | 1372 | Only Step 3.5 Flash measured |
| LMArena Text: entertainment and media | Not measured | 1360 | Only Step 3.5 Flash measured |
| Neither model has a result on the other 26 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Step 3.5 Flash costs less
Repository review
50K input + 3K output tokens
Step 3.5 Flash costs less
Agent loop
200K input + 10K output tokens
Step 3.5 Flash costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Fireworks Ember-1 | StepFun Step 3.5 Flash |
|---|---|---|
| Maker | Fireworks | StepFun |
| Weights | No public weights listed | Open weights |
| Released | September 24, 2026 | January 29, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $3.00 | $0.10 |
| Output $/Mtok | $15.00 | $0.30 |
| Coding index | 52.6 | Not benchmarked |
| Independent measurements behind it | 2 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Ember-1 better than Step 3.5 Flash for coding?
Only Ember-1 has a coding score, 52.6 on the Vibe Coding Index; Step 3.5 Flash has none, so the two cannot be ranked on coding. Step 3.5 Flash has the edge where output tokens cost 50.0x less.
Which is cheaper, Ember-1 or Step 3.5 Flash?
Ember-1 costs $3.00 per million input tokens and $15.00 per million output tokens; Step 3.5 Flash costs $0.10 and $0.30. Cost per solved task is known for neither of them.
Which has the bigger context window, Ember-1 or Step 3.5 Flash?
Ember-1, with 1.05M tokens against 262K.
Has any benchmark tested both Ember-1 and Step 3.5 Flash?
No benchmark has tested both yet. Ember-1 has results on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Code migration (Vals AI); Step 3.5 Flash on Terminal-Bench Hard (Artificial Analysis run), LMArena Text: coding and LMArena Text: software and IT. Compare them on price and context instead. Data as of October 21, 2026.