2026-04-22T21:19:01Z https://benchlist.ai/feed.xml Benchlist https://benchlist.ai/verify/run-voyage-beir-001 2026-04-23T15:15:00Z

Verified run: Voyage AI scored 68.1 on BEIR (model: voyage-3-large). Aligned batch: 0xf02d151fea3bc192a3b4c5d6e7f8009a2f3a4b506182a3d4e5f60819203c4d5.

https://benchlist.ai/verify/run-pinecone-ann-002 2026-04-23T15:00:00Z

Verified run: Pinecone scored 64.3 on BEIR (model: serverless-s1). Aligned batch: 0xef2c141ed93ab192a3b4c5d6e7f8009a2e3f4a506172a3d4e5f608192a3c4d5.

https://benchlist.ai/verify/run-codex-tau-001 2026-04-23T14:45:00Z

Verified run: OpenAI Codex scored 58.2 on τ-Bench (model: codex-pro). Aligned batch: 0xde2b131dc8339192a3b4c5d6e7f80091d2e3f4a50617283c4d5e6f708192a3c4.

https://benchlist.ai/verify/run-devin-tau-001 2026-04-23T14:30:00Z

Verified run: Devin scored 61.0 on τ-Bench (model: devin-v1). Aligned batch: 0xcd2a121cb7328192a3b4c5d6e7f80091c2d3e4f50617182b3c4d5e6f7081a2c3.

https://benchlist.ai/verify/run-rem-gpqa-001 2026-04-23T14:15:00Z

Verified run: REM Labs scored 69.4 on GPQA Diamond (model: rem-v1 @ claude-opus-4-7). Aligned batch: 0xbc29111bb6317192a3b4c5d6e7f80091b2c3d4e5f607182a3b4c5d6e7f80091b.

https://benchlist.ai/verify/run-rem-mmlupro-001 2026-04-23T14:00:00Z

Verified run: REM Labs scored 82.3 on MMLU-Pro (model: rem-v1 @ claude-opus-4-7). Aligned batch: 0xab28101ab5307081a2b3c4d5e6f708192a3b4c5d6e7f80812b3c4d5e6f7081.

https://benchlist.ai/verify/run-mcp-filesystem-compat-001 2026-04-23T13:45:00Z

Verified run: MCP Filesystem scored 98 on MCP Compatibility (model: mcp-filesystem-1.0). Aligned batch: 0x9a270f19b42f708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-mcp-notion-compat-001 2026-04-23T13:30:00Z

Verified run: MCP Notion scored 92 on MCP Compatibility (model: mcp-notion-1.0). Aligned batch: 0x89260e18b32e708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-runloop-sandbox-001 2026-04-23T13:15:00Z

Verified run: Runloop scored 890 on Sandbox Cold Start (model: runloop-bench-v1). Aligned batch: 0x78250d17b22d708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-vectara-frames-001 2026-04-23T13:00:00Z

Verified run: Vectara scored 72.8 on FRAMES (model: vectara-rag). Aligned batch: 0x67240c16b12c708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-autogen-agentbench-001 2026-04-23T12:45:00Z

Verified run: AutoGen scored 47.3 on AgentBench (model: autogen + gpt-5). Aligned batch: 0x56230b15b02b708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-mastra-taubench-001 2026-04-23T12:30:00Z

Verified run: Mastra scored 58.4 on τ-Bench (model: mastra + claude-opus-4-7). Aligned batch: 0x45220a14af2a708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-serper-frames-001 2026-04-23T12:15:00Z

Verified run: Serper scored 70.1 on FRAMES (model: serper-v1). Aligned batch: 0x34210913ae29708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-jina-reader-frames-001 2026-04-23T12:00:00Z

Verified run: Jina Reader scored 68.4 on FRAMES (model: jina-reader-v2). Aligned batch: 0x23200812ad28708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-elevenlabs-rtf-001 2026-04-23T11:45:00Z

Verified run: ElevenLabs scored 0.19 on Voice Real-Time Factor (model: eleven-multilingual-v3). Aligned batch: 0x121f0711ac27708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-deepgram-rtf-001 2026-04-23T11:30:00Z

Verified run: Deepgram scored 0.14 on Voice Real-Time Factor (model: nova-3). Aligned batch: 0x011e0610ab26708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-baseten-tps-001 2026-04-23T11:15:00Z

Verified run: Baseten scored 220 on Inference Throughput (model: llama-3.3-70b). Aligned batch: 0xf11d050f0a25708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-sambanova-tps-001 2026-04-23T11:00:00Z

Verified run: SambaNova Cloud scored 480 on Inference Throughput (model: llama-3.3-70b). Aligned batch: 0xe11c040e0a24708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-milvus-ann-001 2026-04-23T10:45:00Z

Verified run: Milvus scored 96.1 on ANN-Benchmarks (model: milvus-2.5-gpu). Aligned batch: 0xd11b030d0a23708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-codex-swebench-001 2026-04-23T10:30:00Z

Verified run: OpenAI Codex scored 56.3 on SWE-bench Lite (model: codex-pro). Aligned batch: 0xc11a020c0a22708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-factory-swebench-001 2026-04-23T10:15:00Z

Verified run: Factory Droid scored 52.7 on SWE-bench Lite (model: droid-v2). Aligned batch: 0xb119010b0a21708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-cohere-command-mbpp-001 2026-04-23T10:00:00Z

Verified run: Cohere Command scored 79.3 on MBPP (model: command-r-plus). Aligned batch: 0xa118000a0a20708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-mistral-lcb-001 2026-04-23T09:45:00Z

Verified run: Mistral AI scored 51.9 on LiveCodeBench (model: mistral-large-2). Aligned batch: 0x911700090a1f708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-qwen-lcb-001 2026-04-23T09:30:00Z

Verified run: Qwen scored 55.4 on LiveCodeBench (model: qwen-2-5-72b). Aligned batch: 0x811600080a1e708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-llama-lcb-001 2026-04-23T09:15:00Z

Verified run: Meta Llama scored 58.9 on LiveCodeBench (model: llama-4-405b). Aligned batch: 0x711500070a1d708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-kimi-lcb-001 2026-04-23T09:00:00Z

Verified run: Moonshot Kimi scored 54.2 on LiveCodeBench (model: kimi-k2). Aligned batch: 0x611400060a1c708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-deepseek-lcb-001 2026-04-23T08:45:00Z

Verified run: DeepSeek scored 57.8 on LiveCodeBench (model: deepseek-v3). Aligned batch: 0x511300050a1b708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-xai-lcb-001 2026-04-23T08:30:00Z

Verified run: xAI Grok scored 62.1 on LiveCodeBench (model: grok-4). Aligned batch: 0x411200040a1a708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-xai-mbpp-001 2026-04-23T08:15:00Z

Verified run: xAI Grok scored 86.7 on MBPP (model: grok-4). Aligned batch: 0x311100030a19708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-gemini-mbpp-001 2026-04-23T08:00:00Z

Verified run: Google Gemini scored 89.6 on MBPP (model: gemini-2-5-pro). Aligned batch: 0x210100020a18708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091.

https://benchlist.ai/verify/run-helicone-eval-001 2026-04-22T19:00:00Z

Verified run: Helicone scored 82 on MCP Compatibility (model: helicone-proxy). Aligned batch: -.

https://benchlist.ai/verify/run-langfuse-eval-001 2026-04-22T18:00:00Z

Verified run: Langfuse scored 88 on MCP Compatibility (model: langfuse-tracer). Aligned batch: -.

https://benchlist.ai/verify/run-rem-lme-002 2026-04-22T05:00:00Z

Verified run: REM Labs scored 92.4 on LongMemEval (model: rem-v1 @ claude-sonnet-4-6). Aligned batch: 0x11b00f0f1a708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-mcp-github-compat-001 2026-04-22T04:45:00Z

Verified run: MCP GitHub scored 100 on MCP Compatibility (model: mcp-github-1.0). Aligned batch: 0x109f0e0e19708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-rem-mcp-compat-001 2026-04-22T04:30:00Z

Verified run: REM MCP scored 100 on MCP Compatibility (model: rem-mcp-0.4). Aligned batch: 0x0f8e0d0d18708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-llamaparse-doc-001 2026-04-22T04:00:00Z

Verified run: LlamaParse scored 91.8 on DocBench (model: llamaparse-premium). Aligned batch: 0x0e7d0c0c17708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-reducto-doc-001 2026-04-22T03:30:00Z

Verified run: Reducto scored 94.2 on DocBench (model: reducto-1.2). Aligned batch: 0x0d6c0b0b16708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-lakera-injection-001 2026-04-22T03:00:00Z

Verified run: Lakera Guard scored 98.4 on Prompt Injection Recall (model: lakera-guard-v4). Aligned batch: 0x0c5b0a0a15708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-guardrails-injection-001 2026-04-22T02:30:00Z

Verified run: Guardrails AI scored 97.1 on Prompt Injection Recall (model: guardrails-full-suite). Aligned batch: 0x0b4a090914708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-e2b-sandbox-001 2026-04-22T02:00:00Z

Verified run: E2B scored 2300 on Sandbox Cold Start (model: firecracker-prod). Aligned batch: 0x0a39080813708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-daytona-sandbox-001 2026-04-22T01:30:00Z

Verified run: Daytona scored 1250 on Sandbox Cold Start (model: daytona-1.0). Aligned batch: 0x0928070712708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-cartesia-ttft-001 2026-04-22T01:00:00Z

Verified run: Cartesia scored 92 on Time-to-First-Token (model: sonic). Aligned batch: 0x0817060611708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-assemblyai-wer-001 2026-04-22T00:30:00Z

Verified run: AssemblyAI scored 4.4 on LibriSpeech WER (model: universal-v2). Aligned batch: 0x0706050510708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-replicate-tps-001 2026-04-22T00:00:00Z

Verified run: Replicate scored 140 on Inference Throughput (model: llama-3.3-70b). Aligned batch: 0x06f5040409708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-cerebras-tps-001 2026-04-21T23:30:00Z

Verified run: Cerebras Inference scored 2180 on Inference Throughput (model: llama-3.3-70b). Aligned batch: 0x05e4030308708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-jina-mteb-001 2026-04-21T23:00:00Z

Verified run: Jina Embeddings scored 66.1 on MTEB (model: jina-embeddings-v3). Aligned batch: 0x04d3020207708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-openai-embed-mteb-001 2026-04-21T22:40:00Z

Verified run: OpenAI Embeddings scored 64.6 on MTEB (model: text-embedding-3-large). Aligned batch: 0x03c2010106708192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-turbopuffer-ann-001 2026-04-21T22:00:00Z

Verified run: Turbopuffer scored 92.8 on ANN-Benchmarks (model: turbopuffer-v1). Aligned batch: 0x02b100000508192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-lancedb-ann-001 2026-04-21T21:30:00Z

Verified run: LanceDB scored 93.7 on ANN-Benchmarks (model: lancedb-0.18). Aligned batch: 0x01a0ffff408192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.

https://benchlist.ai/verify/run-chroma-ann-001 2026-04-21T21:00:00Z

Verified run: Chroma scored 91.2 on ANN-Benchmarks (model: chroma-0.5). Aligned batch: 0xf89feefe307192a3b4c5d6e7f8091a2b3c4d5e6f708192a3b4c5d6e7f8091a2b.