Parallel (mode=turbo)
Stub model card so this search API can appear on the OB News Websearch Official Benchmark leaderboard. There are no weights here.
- Band: Web search
- Endpoint:
POST /v1/search - Config:
mode=turbo - Docs: https://docs.parallel.ai/api-reference/search/search
- Live board: https://parallel.ai
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Evaluation results
- openbenchmarks/OB-News-Websearch
- Accuracy View evaluation resultssource
POST /v1/search · mode=turbo; $ / 1k correct=$1.40; private held-out 300; extract gpt-5.6-terra medium; judge claude-opus-5 Bedrock71.3 * - Web Search View evaluation resultssource POST /v1/search · mode=turbo; $ / 1k correct=$1.40; private held-out 300; extract gpt-5.6-terra medium; judge claude-opus-5 Bedrock71.3 *
- Ar At 1 View evaluation resultssource POST /v1/search · mode=turbo; $ / 1k correct=$1.40; private held-out 300; extract gpt-5.6-terra medium; judge claude-opus-5 Bedrock45.3 *