Model comparison
GPT-OSS 120B vs Qwen3.5 397B
Head-to-head evidence from 17 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-OSS 120B #116 (Supported); Qwen3.5 397B #71 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-OSS 120B and Qwen3.5 397B share 17 comparable benchmark results. 0 of 8 categories are comparable. 10 results are unique to GPT-OSS 120B; 38 to Qwen3.5 397B.
Updated July 20, 2026- Shared results
- 17
- GPT-OSS 120B only
- 10
- Qwen3.5 397B only
- 38
- Comparable categories
- 0 / 8
Benchmark data for GPT-OSS 120B and Qwen3.5 397B is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 17 shared benchmark results across 5 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.
Qwen3.5 397B is priced at $0.60 input / $3.60 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens 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 | Qwen3.5 397B |
|---|---|---|---|
| Agentic | GPT-OSS 120BNot measured | MarginNo overlap | Qwen3.5 397B56.5 |
| Coding | GPT-OSS 120BNot measured | MarginNo overlap | Qwen3.5 397B66.5 |
| Reasoning | GPT-OSS 120BNot measured | MarginNo overlap | Qwen3.5 397B63.2 |
| Knowledge | GPT-OSS 120BNot measured | MarginNo overlap | Qwen3.5 397B56.6 |
| Math | GPT-OSS 120BNot measured | MarginNo overlap | Qwen3.5 397B90.6 |
| Multilingual | GPT-OSS 120BNot measured | MarginNo overlap | Qwen3.5 397B84.7 |
| Multimodal | GPT-OSS 120BNot measured | MarginNo overlap | Qwen3.5 397B79.6 |
| Inst. Following | GPT-OSS 120BNot measured | MarginNo overlap | Qwen3.5 397B92.6 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-OSS 120B | Qwen3.5 397B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-OSS 120B$0 input / $0 output | Qwen3.5 397B$0.6 input / $3.6 output | GPT-OSS 120B has the lower combined listed price. |
| Generation speedtokens per second | GPT-OSS 120B262 tok/s | Qwen3.5 397B96 tok/s | GPT-OSS 120B has the higher measured throughput. |
| First-answer latencyseconds to first token | GPT-OSS 120B0.79 s | Qwen3.5 397B2.44 s | GPT-OSS 120B reaches the first token sooner. |
| Context windowmaximum listed tokens | GPT-OSS 120B128K | Qwen3.5 397B128K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic21 benchmarks
| Benchmark | GPT-OSS 120B | Qwen3.5 397B | Result |
|---|---|---|---|
| AA Agentic IndexSource | 13.2% | 19.9% | Qwen3.5 397B leads |
| APEX-Agents-AASource | 3.1% | 15.3% | Qwen3.5 397B leads |
| τ²-bench resultsSource | 65.8% | 95.6% | Qwen3.5 397B leads |
| GDPval-AASource | 15.0% | 23.1% | Qwen3.5 397B leads |
| GDPval-AASource | 799 | 962 | Qwen3.5 397B leads |
| Gert LabsSource | 29.61% | 46.76% | Qwen3.5 397B 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 | — | 52.5% | Not comparable |
| BrowseCompSource | — | 62% | Not comparable |
| Claw-EvalSource | — | 56.8% | Not comparable |
| QwenClawBenchSource | — | 51.8% | Not comparable |
| τ³-bench resultsSource | — | 68.4% | Not comparable |
| VITA-BenchSource | — | 43.7% | Not comparable |
| DeepPlanningSource | — | 37.6% | Not comparable |
| ToolathlonSource | — | 36.3% | Not comparable |
| MCP AtlasSource | — | 46.1% | Not comparable |
| MCP-TasksSource | — | 74.2% | Not comparable |
| WideResearchSource | — | 74.0% | Not comparable |
| ResearchClawBenchSource | — | 14.2% | Not comparable |
Coding7 benchmarks
| Benchmark | GPT-OSS 120B | Qwen3.5 397B | Result |
|---|---|---|---|
| React Native EvalsSource | 71.6% | — | Not comparable |
| AA Coding IndexSource | 30.4% | 48.2% | Qwen3.5 397B leads |
| AA-SciCodeSource | 38.9% | 42.0% | Qwen3.5 397B leads |
| AA LiveCodeBenchSource | 87.8% | — | Not comparable |
| SWE-bench VerifiedSource | — | 76.2% | Not comparable |
| LiveCodeBench v6Source | — | 83.6% | Not comparable |
| SWE-bench ProSource | — | 50.9% | Not comparable |
Reasoning4 benchmarks
Knowledge14 benchmarks
| Benchmark | GPT-OSS 120B | Qwen3.5 397B | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 23.8% | 33.7% | Qwen3.5 397B leads |
| AA-GPQA DiamondSource | 78.2% | 89.3% | Qwen3.5 397B leads |
| AA-HLESource | 18.5% | 27.3% | Qwen3.5 397B leads |
| AA-Omniscience IndexSource | -50.0% | -29.8% | Qwen3.5 397B leads |
| AA-Omniscience AccuracySource | 21.5% | 31.4% | Qwen3.5 397B leads |
| AA-Omniscience Hallucination RateSource | 91.2% | 89.1% | Qwen3.5 397B leads |
| AA Openness IndexSource | 38.9% | — | Not comparable |
| AA MMLU-ProSource | 80.8% | — | Not comparable |
| GPQASource | — | 88.4% | Not comparable |
| SuperGPQASource | — | 70.4% | Not comparable |
| MMLU-ProSource | — | 87.8% | Not comparable |
| MMLU-ReduxSource | — | 94.9% | Not comparable |
| C-EvalSource | — | 93% | Not comparable |
| HLESource | — | 28.7% | Not comparable |
Math6 benchmarks
Multilingual3 benchmarks
Multimodal8 benchmarks
| Benchmark | GPT-OSS 120B | Qwen3.5 397B | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1000 | — | Not comparable |
| MMMU-ProSource | — | 79% | Not comparable |
| MathVisionSource | — | 88.6% | Not comparable |
| CharXivSource | — | 80.8% | Not comparable |
| VideoMMMUSource | — | 84.7% | Not comparable |
| ScreenSpot ProSource | — | 65.6% | Not comparable |
| V*Source | — | 95.8% | Not comparable |
| AA-MMMU-ProSource | — | 77.3% | Not comparable |
Frequently Asked Questions (3)
Can I compare GPT-OSS 120B and Qwen3.5 397B 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 Qwen3.5 397B today?
GPT-OSS 120B: $0.00 input / $0.00 output per 1M tokens Qwen3.5 397B: $0.60 input / $3.60 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
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.