Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
BenchLM
Upstage logo
Model A
Solar Pro 4

Upstage

—

Evidence status unavailable

90% interval unavailable

Solar Pro 4 vs Step 3.7 Flash

Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

StepFun logo
Model B
Step 3.7 Flash

StepFun

49.95/100

Estimated · Public rank #125

90% interval 36.1–61.5

Decision reading

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.

1 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

Share on XLinkedInSocial cardCSVJSON

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.

  • Long documents

    Prompts that approach the documented context limit

    Solar Pro 4

    Solar Pro 4 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Step 3.7 Flash

    Step 3.7 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

    Solar Pro 4

    Solar Pro 4 has the lower estimated token cost for this stated workload. 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 3.7 Flash

    Step 3.7 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

    Solar Pro 4 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

    Solar Pro 4 is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

Shared results
1
Solar Pro 4 only
9
Step 3.7 Flash only
10
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.

Agentic

Not comparable
Solar Pro 4
Not ranked
Step 3.7 Flash
48.6
Estimated · #64/152
Basis
BenchAlign lane · 4 vs 7 public rows
Reading
Not comparable

Coding

Not comparable
Solar Pro 4
Not ranked
Step 3.7 Flash
47.1
Estimated · #75/151
Basis
BenchAlign lane · 3 vs 2 public rows
Reading
Not comparable

Reasoning

Not comparable
Solar Pro 4
Not ranked
Step 3.7 Flash
71.7
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Solar Pro 4
Not ranked
Step 3.7 Flash
48.4
Estimated · #92/183
Basis
BenchAlign lane · 2 vs 0 public rows
Reading
Not comparable

Math

Not comparable
Solar Pro 4
Not ranked
Step 3.7 Flash
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Solar Pro 4
Not ranked
Step 3.7 Flash
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Solar Pro 4
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
Solar Pro 4
Not ranked
Step 3.7 Flash
82.1
#52/123
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
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.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

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

Solar Pro 4
$0.0009
Fits in one request
Step 3.7 Flash
$0.00077
Fits in one request

Step 3.7 Flash has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Solar Pro 4
$0.0186
Fits in one request
Step 3.7 Flash
$0.01345
Fits in one request

Step 3.7 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

Solar Pro 4
$0.03
Fits in one request
Step 3.7 Flash
$0.0555
Fits in one request
Cached input priced at the published list-input rate

Solar Pro 4 has the lower modeled cost

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.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Solar Pro 4

$0.06 per 1M cached input tokens

Upstage Solar Pro 4 launch post

Step 3.7 Flash

Not published

Documented inputs

Solar Pro 4

Not sourced

Step 3.7 Flash

Not sourced

Documented outputs

Solar Pro 4

Not sourced

Step 3.7 Flash

Not sourced

Provider availability

Solar Pro 4

Not sourced

Step 3.7 Flash

Not sourced

Reasoning profile

Solar Pro 4

Reasoning

Step 3.7 Flash

Reasoning

Weight access

Solar Pro 4

Proprietary

Step 3.7 Flash

Open Weight

License

Solar Pro 4

Proprietary

Step 3.7 Flash

Open Weight

Release date

Solar Pro 4

2026-08-11

Step 3.7 Flash

2026-05-29

If you already use one of these models
Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost
Repository review: $0.0186 vs $0.01345. Cache-heavy agent loop: $0.03 vs $0.0555.
Context tradeoff
Solar Pro 4 has the larger documented window (512K).

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 evidence20 rows

Agentic

  • Terminal-Bench 2.1

    Solar Pro 457.0%
    Source
    Step 3.7 Flash—

    Not directly comparable

  • BrowseComp

    Solar Pro 449.2%
    Source
    Step 3.7 Flash75.8%
    Source

    Step 3.7 Flash leads this result

  • MCP Atlas

    Solar Pro 461.4%
    Source
    Step 3.7 Flash—

    Not directly comparable

  • APEX-Agents

    Solar Pro 418.7%
    Source
    Step 3.7 Flash—

    Not directly comparable

  • Terminal-Bench 2.0

    Solar Pro 4—
    Step 3.7 Flash59.5%
    Source

    Not directly comparable

  • DeepSearchQA

    Solar Pro 4—
    Step 3.7 Flash92.8%
    Source

    Not directly comparable

  • Toolathlon

    Solar Pro 4—
    Step 3.7 Flash49.5%
    Source

    Not directly comparable

  • Claw-Eval

    Solar Pro 4—
    Step 3.7 Flash67.1%
    Source

    Not directly comparable

  • HLE w/ tools

    Solar Pro 4—
    Step 3.7 Flash47.2%
    Source

    Not directly comparable

  • Gert Labs

    Solar Pro 4—
    Step 3.7 Flash51.57%
    Source

    Not directly comparable

Coding

  • Terminal-Bench 2.1

    Solar Pro 457.0%
    Source
    Step 3.7 Flash—

    Not directly comparable

  • SWE-bench Verified

    Solar Pro 470.6%
    Source
    Step 3.7 Flash—

    Not directly comparable

  • LiveCodeBench

    Solar Pro 487.8%
    Source
    Step 3.7 Flash—

    Not directly comparable

  • SWE-bench Pro

    Solar Pro 4—
    Step 3.7 Flash56.3%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Solar Pro 4—
    Step 3.7 Flash59.5%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    Solar Pro 489.0%
    Source
    Step 3.7 Flash—

    Not directly comparable

  • MMLU-Pro

    Solar Pro 486.3%
    Source
    Step 3.7 Flash—

    Not directly comparable

Math

  • AIME26

    Solar Pro 495.3%
    Source
    Step 3.7 Flash—

    Not directly comparable

Multimodal

  • SimpleVQA

    Solar Pro 4—
    Step 3.7 Flash79.2%
    Source

    Not directly comparable

  • V*

    Solar Pro 4—
    Step 3.7 Flash95.3%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Solar Pro 4 or Step 3.7 Flash?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Solar Pro 4 or Step 3.7 Flash?

Solar Pro 4 is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Solar Pro 4 or Step 3.7 Flash?

Solar Pro 4 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Solar Pro 4 or Step 3.7 Flash?

For the stated presets, chat costs $0.0009 on Solar Pro 4 and $0.00077 on Step 3.7 Flash; repository review costs $0.0186 and $0.01345; the cache-heavy agent loop costs $0.03 and $0.0555. Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Solar Pro 4 or Step 3.7 Flash?

Solar Pro 4 has the larger documented context window: 512K, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 10, 2026

Watch Solar Pro 4 vs Step 3.7 Flash

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.