Model comparison
GPT-5 Mini vs Step 3.5 Flash
GPT-5 Mini and Step 3.5 Flash score almost the same on the Noometry Index (41.8 vs 42.3), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. GPT-5 Mini scores higher in 4 categories and Step 3.5 Flash in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Mini leads 45.6 to 39.6.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- GPT-5 Mini accepts more context: 400K tokens versus 256K.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | Step 3.5 Flash | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 41.8 | 42.3 |
| Released | 2025-08-07 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | 400K | 256K |
| Max output | 128K | 256K |
| Input $ / M tokens | $0.25 | $0.10 |
| Output $ / M tokens | $2 | $0.30 |
| Results tracked | 60 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
GPT-5 Mini: 40.1 (#146), Step 3.5 Flash: 42.4 (#105)
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1406 | 1436 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| WeirdML | 52.7% | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.1 (#70), Step 3.5 Flash: —
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 23.9 (#168), Step 3.5 Flash: 22.2 (#202)
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1380 | 1411 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| Epoch Capabilities Index | 145.52 | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), Step 3.5 Flash: 42.6 (#84)
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1378 | 1408 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Step 3.5 Flash: 39.6 (#132)
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1379 | 1421 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), Step 3.5 Flash: —
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual Step 3.5 Flash leads
GPT-5 Mini: 48.9 (#137), Step 3.5 Flash: 50.5 (#119)
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1363 | 1385 |
| LMArena Chinese | 1385 | 1447 |
| LMArena French | 1386 | 1421 |
| LMArena German | 1366 | 1405 |
| LMArena Japanese | 1341 | 1354 |
| LMArena Korean | 1308 | 1352 |
| LMArena Russian | 1362 | 1385 |
| LMArena Spanish | 1355 | 1419 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Step 3.5 Flash: 73.1 (#124)
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1357 | 1385 |
| IFEval | 92.7% | — |
Long Context Too close to call
GPT-5 Mini: 41.9 (#132), Step 3.5 Flash: 42.8 (#117)
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1355 | 1402 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference Step 3.5 Flash leads
GPT-5 Mini: 55.2 (#148), Step 3.5 Flash: 58.8 (#113)
| Benchmark | GPT-5 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1373 | 1403 |
| LMArena Creative Writing | 1325 | 1357 |
| LMArena Multi-Turn | 1363 | 1405 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than Step 3.5 Flash?
GPT-5 Mini and Step 3.5 Flash score almost the same on the Noometry Index (41.8 vs 42.3), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5 Mini or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is GPT-5 Mini or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 256K.
How many benchmarks do GPT-5 Mini and Step 3.5 Flash share?
17 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Step 3.5 Flash has 19.