Data points: 147
The readout for GPT-OSS and Qwen3.5, before the detailed comparison sheet.
Decision read
GPT-OSS
GPT-OSS currently has the stronger profile, with verified wins split 5 to 1.
Evidence depth
147 data points
Includes 35 benchmark rows, 2 audit samples, and 8 provider examples.
Selection signal
Start with GPT-OSS
The charts below split 45 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
Model compare GPT-OSS vs Qwen3.5gpt-oss-vs-qwen3-5 | Model A GPT-OSS | Model B Qwen3.5 |
|---|---|---|
| Overall leader | Leading | Contender |
| Verified metric wins | 5 wins | 1 wins |
| Where it leads | Cheapest input price, Average speed, First-token latency, Provider coverage, Recent tests |
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
GPT-OSS
57.1
Avg. score
Qwen3.5
67.7
Selected category
Multimodal
GPT-OSS leads by 21.6
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
GPT-OSS
35.0
Rank #61/82 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner62.0
Rank #33/82 · confidence 4 · eval date 2026-02-16
GPT-OSS
winner322.0 tok/s
Rank #2/78 · confidence 4
Qwen3.5
51.9 tok/s
Rank #60/78 · confidence 4
GPT-OSS
winner0.51 s
Rank #6/78 · confidence 4
Qwen3.5
1.75 s
Rank #50/78 · confidence 4
GPT-OSS
winner6.72 s
Rank #41/78 · confidence 4
Qwen3.5
63.12 s
Rank #72/78 · confidence 4
GPT-OSS
winner$0.262/M
Rank #13/95 · confidence 4
Qwen3.5
$1.35/M
Rank #51/95 · confidence 4
GPT-OSS
winner$0.150/M
Rank #13/95 · confidence 4
Qwen3.5
$0.600/M
Rank #45/95 · confidence 4
GPT-OSS
winner$0.600/M
Rank #15/95 · confidence 4
Qwen3.5
$3.60/M
Rank #53/95 · confidence 4
GPT-OSS
77.5%
Rank #53/74 · confidence 4
Qwen3.5
winner87.8%
Rank #5/74 · confidence 4 · eval date 2026-02-16
GPT-OSS
67.2%
Rank #73/103 · confidence 4
Qwen3.5
winner89.3%
Rank #14/103 · confidence 4
GPT-OSS
5.2%
Rank #73/103 · confidence 4
Qwen3.5
winner27.3%
Rank #22/103 · confidence 4
GPT-OSS
31.7
Rank #47/58 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner57.4
Rank #30/58 · confidence 4 · eval date 2026-02-16
GPT-OSS
winner1.1
Rank #31/44 · confidence 1 · eval date 2025-08-05
Qwen3.5
0.9
Rank #36/44 · confidence 4 · eval date 2026-02-16
GPT-OSS
50.7
Rank #41/57 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner58.0
Rank #37/57 · confidence 4 · eval date 2026-02-16
GPT-OSS
23.5
Rank #43/59 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner35.6
Rank #26/59 · confidence 4 · eval date 2026-02-16
GPT-OSS
28.6
Rank #41/61 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner37.4
Rank #28/61 · confidence 4 · eval date 2026-02-16
GPT-OSS
38.9
Rank #40/63 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner41.1
Rank #32/63 · confidence 4 · eval date 2026-02-16
GPT-OSS
22.5
Rank #67/70 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner66.6
Rank #35/70 · confidence 4 · eval date 2026-02-16
GPT-OSS
36.0%
Rank #65/101 · confidence 4
Qwen3.5
winner42.0%
Rank #37/101 · confidence 4
GPT-OSS
28.5
Rank #44/51 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner68.2
Rank #23/51 · confidence 4 · eval date 2026-02-16
GPT-OSS
winner91.2
Rank #4/58 · confidence 1 · eval date 2025-08-05
Qwen3.5
79.8
Rank #25/58 · confidence 4 · eval date 2026-02-16
GPT-OSS
78.2
Rank #40/63 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner86.1
Rank #21/63 · confidence 4 · eval date 2026-02-16
GPT-OSS
44.5
Rank #52/67 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner71.1
Rank #24/67 · confidence 4 · eval date 2026-02-16
GPT-OSS
18.5
Rank #33/63 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner18.8
Rank #31/63 · confidence 4 · eval date 2026-02-16
GPT-OSS
23.8
Rank #43/66 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner32.0
Rank #34/66 · confidence 4 · eval date 2026-02-16
GPT-OSS
21.5
Rank #49/58 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner24.3
Rank #40/58 · confidence 4 · eval date 2026-02-16
GPT-OSS
35.3
Rank #40/51 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner71.8
Rank #16/51 · confidence 4 · eval date 2026-02-16
GPT-OSS
23.2
Rank #53/60 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner65.1
Rank #25/60 · confidence 4 · eval date 2026-02-16
GPT-OSS
42.6
Rank #53/58 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner84.8
Rank #12/58 · confidence 4 · eval date 2026-02-16
GPT-OSS
winner69.0
Rank #26/60 · confidence 1 · eval date 2025-08-05
Qwen3.5
51.6
Rank #34/60 · confidence 4 · eval date 2026-02-16
GPT-OSS
13.8
Rank #13/14 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner24.0
Rank #11/14 · confidence 3 · eval date 2026-03-04
GPT-OSS
775.0
Rank #14/16 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner979.0
Rank #12/16 · confidence 3 · eval date 2026-03-04
GPT-OSS
29.6
Rank #34/36 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner46.8
Rank #21/36 · confidence 4 · eval date 2026-02-16
GPT-OSS
37.9
Rank #38/57 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner53.3
Rank #26/57 · confidence 4 · eval date 2026-02-16
GPT-OSS
65.8
Rank #39/58 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner83.9
Rank #26/58 · confidence 4 · eval date 2026-02-16
GPT-OSS
35.7
Rank #53/69 · confidence 1 · eval date 2025-08-05
Qwen3.5
winner54.0
Rank #33/69 · confidence 4 · eval date 2026-02-16
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-OSS | Qwen3.5 |
|---|---|---|
Winner: Qwen3.5 | GPT-OSS openai/gpt-oss-120b No audit yet | Qwen3.5 qwen/qwen3.5-122b-a10b |
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | GPT-OSS | Qwen3.5 |
|---|---|---|
295 tests | GPT-OSS speed / latency 154 tok/s / 963ms input / output No data |
This report only uses LMSpeed data for GPT-OSS and Qwen3.5: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | GPT-OSS | Qwen3.5 |
|---|---|---|
| When to choose each model | GPT-OSS GPT-OSS is stronger when you prioritize Cheapest input price, Average speed, First-token latency, Provider coverage, Recent tests. | Qwen3.5 Qwen3.5 is stronger when you prioritize Free providers. |
TL;DR: GPT-OSS leads across 147 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from GPT-OSS vs Qwen3.5 into nearby model comparisons with enough verified LMSpeed data.
| Free providers |
| Model metadata | GPT-OSS exposes 131.1K tokens; notable signals: Text input, Text output, Tool calling, Reasoning. | Qwen3.5 exposes 262.1K tokens; notable signals: Text input, Image input, Text output, Tool calling. |
|---|---|---|
| Developer | No data | No data |
| Context window | 131.1K tokens | 262.1K tokens |
| Max output | 131.1K tokens | 262.1K tokens |
| Released | Aug 2025 | Mar 2026 |
| Modalities | Input Text Output Text | Input TextImagevideo Output Text |
| Features | Text inputText outputTool callingReasoning | Text inputImage inputText outputTool callingStructured outputsJSON modeReasoning |
| Parameters | 120B | 9B |
| Tokenizer | GPT | Qwen3 |
| Knowledge cutoff | 2024-06-30 | No data |
| OpenRouter ID | openai/gpt-oss-120b:free | qwen/qwen3.5-9b |
| References | No data | No data |
Audit score
89
小水管 APIWinner: GPT-OSS | GPT-OSS gpt-oss-20b Audit score 79 648468100 | Qwen3.5 qwen3.5-2b No audit yet |
|---|
Qwen3.5
speed / latency
37 tok/s / 8257ms
input / output
No data
OpenRouter40 tests | GPT-OSS speed / latency 41 tok/s / 2851ms input / output No data | Qwen3.5 speed / latency N/A / N/A input / output No data |
|---|
素墨API35 tests | GPT-OSS speed / latency 347 tok/s / 2670ms input / output No data | Qwen3.5 speed / latency N/A / N/A input / output No data |
|---|
GPT Load (PP.UA)30 tests | GPT-OSS speed / latency 583 tok/s / 1259ms input / output No data | Qwen3.5 speed / latency 61 tok/s / 781ms input / output No data |
|---|
小水管 API30 tests | GPT-OSS speed / latency 1047 tok/s / 867ms input / output No data | Qwen3.5 speed / latency N/A / N/A input / output No data |
|---|
GPT-OSS openai/gpt-oss-120b speed / latency No data input / output $1.00/M / $1.00/M | Qwen3.5 qwen/qwen3.5-122b-a10b speed / latency No data input / output $0/M / $0/M |
GPT-OSS openai/gpt-oss-120b speed / latency No data input / output $100.00/M / $1000.00/M | Qwen3.5 qwen/qwen3.5-397b-a17b speed / latency No data input / output $0/M / $0/M |
GPT-OSS openai/gpt-oss-20b:free speed / latency No data input / output $0/M / $0/M | Qwen3.5 qwen3.5-397b-a17b speed / latency No data input / output $0.600/M / $3.00/M |
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
