Agentic
Not comparable- Step 3.5 Flash
- Not ranked
- Step 3.7 Flash
- 46.1
- Estimated · #87/151
- Basis
- BenchAlign lane · 0 vs 7 public rows
- Reading
- Not comparable
Step 3.5 Flash vs Step 3.7 Flash
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.
0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Chat turn cost
1K fresh input + 500 output tokens
Step 3.5 Flash
Step 3.5 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Step 3.5 Flash
Step 3.5 Flash has the lower estimated token cost for this stated workload. Step 3.5 Flash has no published cached-input rate, so cached tokens use its listed input rate. Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Step 3.5 Flash
Step 3.5 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Step 3.5 Flash is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Step 3.5 Flash is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
11 Step 3.7 Flash only
- Shared results
- 0
- Step 3.5 Flash only
- 0
- Step 3.7 Flash only
- 11
- Like-for-like categories
- 0 / 8
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Coding
Not comparable- Step 3.5 Flash
- Not ranked
- Step 3.7 Flash
- 49.7
- Estimated · #75/183
- Basis
- BenchAlign lane · 0 vs 2 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Step 3.5 Flash
- Not ranked
- Step 3.7 Flash
- 71.1
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Step 3.5 Flash
- Not ranked
- Step 3.7 Flash
- 50.3
- Estimated · #87/181
- Basis
- BenchAlign lane · 0 vs 0 public rows
- Reading
- Not comparable
Math
Not comparable- Step 3.5 Flash
- Not ranked
- Step 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Step 3.5 Flash
- Not ranked
- Step 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Step 3.5 Flash
- Not ranked
- Step 3.7 Flash
- 70.9
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Step 3.5 Flash
- Not ranked
- Step 3.7 Flash
- 81.8
- #51/120
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Step 3.5 Flash | Step 3.7 Flash | Basis | Reading |
|---|---|---|---|---|
| Agentic | Not ranked | 46.1Estimated · #87/151 | Not comparableBenchAlign lane · 0 vs 7 public rows | Not comparable |
| Coding | Not ranked | 49.7Estimated · #75/183 | Not comparableBenchAlign lane · 0 vs 2 public rows | Not comparable |
| Reasoning | Not ranked | 71.1Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Knowledge | Not ranked | 50.3Estimated · #87/181 | Not comparableBenchAlign lane · 0 vs 0 public rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 70.9Unranked · 3 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 81.8#51/120 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Step 3.5 Flash
- $0.00025
- Fits in one request
- Step 3.7 Flash
- $0.00077
- Fits in one request
Step 3.5 Flash has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Step 3.5 Flash
- $0.0059
- Fits in one request
- Step 3.7 Flash
- $0.01345
- Fits in one request
Step 3.5 Flash has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Step 3.5 Flash
- $0.025
- Fits in one request
- Cached input priced at the published list-input rate
- Step 3.7 Flash
- $0.0555
- Fits in one request
- Cached input priced at the published list-input rate
Step 3.5 Flash has the lower modeled cost
Step 3.5 Flash has no published cached-input rate, so cached tokens use its listed input rate. Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationStep 3.5 FlashStep 3.7 Flash
Context window
Maximum documented context; output-token limits may be lower.
Step 3.5 Flash
256K
Step 3.7 Flash
256K
API model ID
Step 3.5 Flash
Not sourced
Step 3.7 Flash
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Step 3.5 Flash
Not published
Step 3.7 Flash
Not published
Documented inputs
Step 3.5 Flash
Not sourced
Step 3.7 Flash
Not sourced
Documented outputs
Step 3.5 Flash
Not sourced
Step 3.7 Flash
Not sourced
Provider availability
Step 3.5 Flash
Not sourced
Step 3.7 Flash
Not sourced
Reasoning profile
Step 3.5 Flash
Non-Reasoning
Step 3.7 Flash
Reasoning
Weight access
Step 3.5 Flash
Open Weight
Step 3.7 Flash
Open Weight
License
Step 3.5 Flash
Open Weight
Step 3.7 Flash
Open Weight
Release date
Step 3.5 Flash
2026-01-20
Step 3.7 Flash
2026-05-29
If you are considering the documented upgrade path
- Deployment change
- Both entries list StepFun as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
- Workload cost
- Repository review: $0.0059 vs $0.01345. Cache-heavy agent loop: $0.025 vs $0.0555.
- Context tradeoff
- Both models list 256K.
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence11 rows
Agentic
Terminal-Bench 2.0
Step 3.5 Flash—Step 3.7 Flash59.5%SourceNot directly comparable
BrowseComp
Step 3.5 Flash—Step 3.7 Flash75.8%SourceNot directly comparable
DeepSearchQA
Step 3.5 Flash—Step 3.7 Flash92.8%SourceNot directly comparable
Toolathlon
Step 3.5 Flash—Step 3.7 Flash49.5%SourceNot directly comparable
Claw-Eval
Step 3.5 Flash—Step 3.7 Flash67.1%SourceNot directly comparable
HLE w/ tools
Step 3.5 Flash—Step 3.7 Flash47.2%SourceNot directly comparable
Gert Labs
Step 3.5 Flash—Step 3.7 Flash51.57%SourceNot directly comparable
Coding
Multimodal
Frequently asked questions
Which is better, Step 3.5 Flash or Step 3.7 Flash?
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Step 3.5 Flash or Step 3.7 Flash?
Step 3.5 Flash is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Step 3.5 Flash or Step 3.7 Flash?
Step 3.5 Flash is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Step 3.5 Flash or Step 3.7 Flash?
For the stated presets, chat costs $0.00025 on Step 3.5 Flash and $0.00077 on Step 3.7 Flash; repository review costs $0.0059 and $0.01345; the cache-heavy agent loop costs $0.025 and $0.0555. Step 3.5 Flash has no published cached-input rate, so cached tokens use its listed input rate. Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Step 3.5 Flash or Step 3.7 Flash?
Both models list the same context window, 256K.
Related comparisons
Last updated September 4, 2026
Watch Step 3.5 Flash vs Step 3.7 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.