Model comparison
GPT-OSS 120B vs Step 3.7 Flash
Head-to-head evidence from 19 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
BenchAlign evidence: GPT-OSS 120B supported; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-OSS 120B and Step 3.7 Flash share 19 comparable benchmark results. 0 of 8 categories are comparable. 9 results are unique to GPT-OSS 120B; 11 to Step 3.7 Flash.
Updated July 16, 2026- Shared results
- 19
- GPT-OSS 120B only
- 9
- Step 3.7 Flash only
- 11
- Comparable categories
- 0 / 8
Benchmark data for GPT-OSS 120B and Step 3.7 Flash is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Step 3.7 Flash is priced at $0.20 input / $1.15 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for GPT-OSS 120B. Step 3.7 Flash has the larger context window at 256K, compared with 128K for GPT-OSS 120B.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | GPT-OSS 120B | Δ | Step 3.7 Flash |
|---|---|---|---|
| Agentic | GPT-OSS 120BNot measured | MarginNo overlap | Step 3.7 Flash66.4 |
| Coding | GPT-OSS 120BNot measured | MarginNo overlap | Step 3.7 Flash56.3 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-OSS 120B | Step 3.7 Flash | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-OSS 120B$0 input / $0 output | Step 3.7 Flash$0.2 input / $1.15 output | GPT-OSS 120B has the lower combined listed price. |
| Generation speedtokens per second | GPT-OSS 120B262 tok/s | Step 3.7 FlashNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-OSS 120B0.79 s | Step 3.7 FlashNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-OSS 120B128K | Step 3.7 Flash256K | Step 3.7 Flash lists the larger context window. |
Benchmark Deep Dive
Agentic15 benchmarks
| Benchmark | GPT-OSS 120B | Step 3.7 Flash | Result |
|---|---|---|---|
| AA Agentic IndexSource | 13.2% | 21.5% | Step 3.7 Flash leads |
| APEX-Agents-AASource | 3.1% | 14.8% | Step 3.7 Flash leads |
| τ²-bench resultsSource | 65.8% | 98.5% | Step 3.7 Flash leads |
| GDPval-AASource | 15.0% | 25.9% | Step 3.7 Flash leads |
| GDPval-AASource | 799 | 1017 | Step 3.7 Flash leads |
| Gert LabsSource | 29.61% | 51.57% | Step 3.7 Flash leads |
| AA EnterpriseOps-GymSource | 25.5% | — | Not comparable |
| AA Harvey LABSource | 0.0% | — | Not comparable |
| AA ITBenchSource | 5.6% | — | Not comparable |
| Terminal-Bench 2.0Source | — | 59.5% | Not comparable |
| BrowseCompSource | — | 75.8% | Not comparable |
| DeepSearchQASource | — | 92.8% | Not comparable |
| ToolathlonSource | — | 49.5% | Not comparable |
| Claw-EvalSource | — | 67.1% | Not comparable |
| HLE w/ toolsSource | — | 47.2% | Not comparable |
Coding7 benchmarks
| Benchmark | GPT-OSS 120B | Step 3.7 Flash | Result |
|---|---|---|---|
| React Native EvalsSource | 71.6% | — | Not comparable |
| AA Coding IndexSource | 30.4% | 39.6% | Step 3.7 Flash leads |
| Terminal-Bench HardSource | 23.5% | 35.6% | Step 3.7 Flash leads |
| AA-SciCodeSource | 38.9% | 40.0% | Step 3.7 Flash leads |
| AA LiveCodeBenchSource | 87.8% | — | Not comparable |
| SWE-bench ProSource | — | 56.3% | Not comparable |
| Terminal-Bench 2.0Source | — | 59.5% | Not comparable |
Reasoning2 benchmarks
Knowledge8 benchmarks
| Benchmark | GPT-OSS 120B | Step 3.7 Flash | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 23.8% | 30.3% | Step 3.7 Flash leads |
| AA-GPQA DiamondSource | 78.2% | 80.9% | Step 3.7 Flash leads |
| AA-HLESource | 18.5% | 19.9% | Step 3.7 Flash leads |
| AA-Omniscience IndexSource | -50.0% | -37.5% | Step 3.7 Flash leads |
| AA-Omniscience AccuracySource | 21.5% | 25.4% | Step 3.7 Flash leads |
| AA-Omniscience Hallucination RateSource | 91.2% | 84.4% | Step 3.7 Flash leads |
| AA Openness IndexSource | 38.9% | — | Not comparable |
| AA MMLU-ProSource | 80.8% | — | Not comparable |
Math1 benchmarks
| Benchmark | GPT-OSS 120B | Step 3.7 Flash | Result |
|---|---|---|---|
| AA AIME 2025Source | 93.4% | — | Not comparable |
Multilingual1 benchmarks
| Benchmark | GPT-OSS 120B | Step 3.7 Flash | Result |
|---|---|---|---|
| AA Global-MMLU-LiteSource | 82.8% | — | Not comparable |
Multimodal4 benchmarks
Inst. Following1 benchmarks
| Benchmark | GPT-OSS 120B | Step 3.7 Flash | Result |
|---|---|---|---|
| AA-IFBenchSource | 69.0% | 67.3% | GPT-OSS 120B leads |
Frequently Asked Questions (3)
Can I compare GPT-OSS 120B and Step 3.7 Flash on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for GPT-OSS 120B and Step 3.7 Flash today?
GPT-OSS 120B: $0.00 input / $0.00 output per 1M tokens Step 3.7 Flash: $0.20 input / $1.15 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.