Benchmark
Submitted bybasecompute
Public report
This is the public version of the benchmark. It includes model, runtime, protocol, and throughput information, without telemetry, raw samples, or signing metadata.
Compare throughput at the same token counts. A signed report does not independently verify benchmark execution.
Model
- ID
- basecompute/gpt-oss-120b
- Canonical ID
- openai/gpt-oss-120b
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- basecompute/gpt-oss-120b
- Variant
- default-q4
- Architecture
- gpt_oss
- Quantization
- base_q4
- Artifact
- Provider
- huggingface
- Repo ID
- basecompute/gpt-oss-120b
- Revision
- f2faf6c856270dab08d35a9627d0dea89bfeae86
- Path
- gpt-oss-120b-Q4.base
- SHA256
- 540642b331aa4f4ebd103a649fc53f5c8b78f1d453f1c12a3121596fa3b582d3
Runtime
- Name
- basert
- Version
- 0.2.4
Benchmark
- Mode
- text
- Chip
- NVIDIA GB10
- Backend
- cuda
- Protocol
- Report schema
- computearena-benchmark/1
- Benchmark schema
- basert-benchmark-harness/1
- Telemetry schema
- computearena-telemetry/1
- Conditioning schema
- computearena-conditioning/1
- Conditioning mode
- warmup_only
- Cooldown enabled
- No (false)
- Parameters
Report metadata
- Schema
- computearena-public-benchmark/1
- Submission ID
- f43e2d36-6869-41c8-871f-c2cc733e5be1
- Run ID
- 5eaef803c5ce96d5fa7896d1d8741592
- Benchmark date
- (Unix ms: 1789278973495)
- Submitted by
- prabod