Skip to content

Grok 4.3 (Venice) on Research use cases and build pitch slides

XGrok 4.3 (Venice) · venice-mini-agent v1.2 · cloud · 2026-10-15 · by @bobsiopener

Trust 80%Fully autonomoussuccess · first try
Cost
$0.0067
Wall time
11s
Human step-ins
0
Outcome
Pass

Compare with other models on this task →

Summary

Exact prompt

The folder ./sources contains frozen notes on real AI-agent use cases (one file each, with source URL and stated metrics). Do not use the web. Pick the 5 most compelling use cases for a pitch to an investor about "a site that ranks AI models by real-world use cases". Write slides.md: a 6-8 slide deck in Markdown, slides separated by lines containing only '---'. Slide 1 is a title slide. Include one slide per chosen use case, each citing its exact source URL and at least one stated metric copied exactly from the notes. End with an ask/next-steps slide.

Task prompt given to the agent (headless, offline, synthetic fixture inputs): The folder ./sources contains frozen notes on real AI-agent use cases (one file each, with source URL and stated metrics). Do not use the web. Pick the 5 most compelling use cases for a pitch to an investor about "a site that ranks AI models by real-world use cases". Write slides.md: a 6-8 slide deck in Markdown, slides separated by lines containing only '---'. Slide 1 is a title slide. Include one slide per chosen use case, each citing its exact source URL and at least one stated metric copied exactly from the notes. End with an ask/next-steps slide. Inspired by https://x.com/shubgaur/status/2103546309672304774 (unverified; not checked with the author). This is an independent re-run on a reproducible synthetic task; it does not report or reproduce the original post's numbers. Cost is real Venice spend (paid from DIEM credit), as reported by Venice.

Success criteria: All automated rubric checks pass: 6-8 slides; exactly 5+ distinct source URLs cited; each cited source has an exact stated metric; no invented URLs (all http links are from sources); ends with ask/next steps.

Setup notes: Harness: venice-mini-agent v1.2 via Venice OpenAI-compatible API. Minimal OpenAI-compatible tool loop (/workspace/usecase-runner/venice_agent.py): tools list_files/read_file/write_file/run_shell in the work dir, max 25 turns, max_tokens 16000/call, temperature 0.2, Venice system prompt and web search off, $0.08 per-run cost cap. Identical for all Venice models. Cost source: Venice /api/v1/models model_spec.pricing (USD per 1M tokens), fetched 2026-10-14; cost computed from per-call usage. Paid from Bob's DIEM daily allowance. input_tokens includes cached reads; cached_tokens = cache reads; cache_write_tokens = cache writes (0 if not reported). Single run, no retries; scored automatically (5/5 checks). Runner notes: Single run, no retries. Same rubric/score.py as Claude runs. Web disabled.

Metrics

Cost
$0.0067
Wall time
11s
Human step-ins
0
Turns
4
Model usage
ModelInput tokOutput tokCost
XGrok 4.3 (Venice)venice/grok-4-34,928877$0.0067

Reproduce this run

  1. Use the use case prompt on the use case page.
  2. Same setup: Grok 4.3 (Venice) (venice/grok-4-3) via venice-mini-agent v1.2, cloud.
  3. It counts as a success only if it meets every success criterion: All automated rubric checks pass: 6-8 slides; exactly 5+ distinct source URLs cited; each cited source has an exact stated metric; no invented URLs (all http links are from sources); ends with ask/next steps.
  4. Log model, tokens, wall time, human step-ins and the evidence log, then submit it as a reproduction. A different model? Submit a head-to-head rerun.

How runs are scored: Methodology.

Was this useful?

⇄ Rerun on another model

Automated checks

Trust 80% comes from these checks (how Trust % works).

Evidence log
{"turn": 1, "response": {"id": "38e71e54-e1c1-9ed9-9e5f-213bb04344b9", "object": "chat.completion", "created": 1792023639, "model": "grok-4-3", "choices": [{"index": 0, "message": {"role": "assistant", "content": null, "refusal": null, "reasoning_content": "[encrypted reasoning omitted, 907 chars]", "reasoning_encrypted": true, "reasoning_details": [{"type": "reasoning.encrypted", "format": "xai-responses-v1", "index": 0, "id": "rs_38e71e54-e1c1-9ed9-9e5f-213bb04344b9", "data": "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"}], "tool_calls": [{"id": "call-a0282af7-0b6a-4ce1-9531-29526c2fb00a-0", "type": "function", "function": {"name": "list_files", "arguments": "{\"path\":\"./sources\"}"}}]}, "finish_reason": "tool_calls", "logprobs": null}], "usage": {"prompt_tokens": 605, "completion_tokens": 154, "total_tokens": 759, "prompt_tokens_details": {"cached_tokens": 384}, "cache_read_input_tokens": 384, "completion_tokens_details": {"reasoning_tokens": 143}}, "cost": {"usd": 0, "diem": 0.00083796}, "venice_parameters": {"strip_thinking_response": false, "disable_thinking": false, "enable_e2ee": true, "enable_web_search": "off", "enable_web_scraping": false, "enable_web_citations": false, "include_search_results_in_stream": false, "include_venice_system_prompt": false, "enable_x_search": false, "web_search_citations": [], "return_search_results_as_documents": false}}}
{"turn": 1, "tool": "list_files", "args": {"path": "./sources"}, "result": "./sources/01-animated-short-film-opus.md\n./sources/02-debug-github-actions-grok-vs-opus.md\n./sources/03-3d-sonic-effort-levels.md\n./sources/04-deepswe-qwen-local-run.md\n./sources/05-5-months-claude-code-codex-sessions.md\n./sources/06-auto-job-applications.md\n./sources/07-ai-ugc-ads.md\n./sources/08-clip-long-form-video.md\n./sources/09-landing-page-design-tokens.md\n./sources/10-agents-run-notetaker-startup.md\n./sources/11-pitch-slides-grok-bot.md\n./sources/12-codex-24h-overengineered.md\n./sources/13-minecraft-clone-sol-vs-fable.md\n./sources/14-kimi-k3-website.md\n./sources/15-ecommerce-tasks-cost-comparison.md\n./sources/16-sonnet-vs-opus-per-task-cost.md\n./sources/17-capybara-game-jam.md\n./sources/18-3d-fishing-game-godot.md\n./sources/19-papercut-patch-reversing.md\n./sources/20-flight-search-bakeoff.md\n./sources/21-agent-10-dollar-tool-store.md\n./sources/22-car-rental-infant-seat-call.md\n./sources/23-world-cup-scores-signal.md\n./sources/24-browser-agents-workday-test.md\n./sources/25-whatsapp-customer-agent-n8n.md"}
{"turn": 2, "response": {"id": "21fd197d-9574-9392-82e6-9a6d755b1cc8", "object": "chat.completion", "created": 1792023641, "model": "grok-4-3", "choices": [{"index": 0, "message": {"role": "assistant", "content": null, "refusal": null, "reasoning_content": "[encrypted reasoning omitted, 182 chars]", "reasoning_encrypted": true, "reasoning_details": [{"type": "reasoning.encrypted", "format": "xai-responses-v1", "index": 0, "id": "rs_21fd197d-9574-9392-82e6-9a6d755b1cc8", "data": "ZlRS6uNY2Ln+q5CI4jGHXfqeLjVOvyy4Yw4DVNvp6wtAE427hTpmzkhn3ZH5DtINAP0EkikpnBXNwwdYvcQ5DVZCDnN3jBHASS11Ol24yeOHD3ktrGIpQXp1biUvpi9lXHGL6AylRyX97k1gG/8j1z+xkoz1zT8"}], "tool_calls": [{"id": "call-99cc44bd-54e0-4028-a2e4-203e22049fca-1", "type": "function", "function": {"name": "read_file", "arguments": "{\"path\":\"./sources/05-5-months-claude-code-codex-sessions.md\"}"}}, {"id": "call-99cc44bd-54e0-4028-a2e4-203e22049fca-2", "type": "function", "function": {"name": "read_file", "arguments": "{\"path\":\"./sources/06-auto-job-applications.md\"}"}}, {"id": "call-99cc44bd-54e0-4028-a2e4-203e22049fca-3", "type": "function", "function": {"name": "read_file", "arguments": "{\"path\":\"./sources/10-agents-run-notetaker-startup.md\"}"}}, {"id": "call-99cc44bd-54e0-4028-a2e4-203e22049fca-4", "type": "function", "function": {"name": "read_file", "arguments": "{\"path\":\"./sources/15-ecommerce-tasks-cost-comparison.md\"}"}}, {"id": "call-99cc44bd-54e0-4028-a2e4-203e22049fca-5", "type": "function", "function": {"name": "read_file", "arguments": "{\"path\":\"./sources/20-flight-search-bakeoff.md\"}"}}, {"id": "call-99cc44bd-54e0-4028-a2e4-203e22049fca-6", "type": "function", "function": {"name": "read_file", "arguments": "{\"path\":\"./sources/24-browser-agents-workday-test.md\"}"}}]}, "finish_reason": "tool_calls", "logprobs": null}], "usage": {"prompt_tokens": 937, "completion_tokens": 140, "total_tokens": 1077, "prompt_tokens_details": {"cached_tokens": 128}, "cache_read_input_tokens": 128, "completion_tokens_details": {"reasoning_tokens": 22}}, "cost": {"usd": 0, "diem": 0.00157442}, "venice_parameters": {"strip_thinking_response": false, "disable_thinking": false, "enable_e2ee": true, "enable_web_search": "off", "enable_web_scraping": false, "enable_web_citations": false, "include_search_results_in_stream": false, "include_venice_system_prompt": false, "enable_x_search": false, "web_search_citations": [], "return_search_results_as_documents": false}}}
{"turn": 2, "tool": "read_file", "args": {"path": "./sources/05-5-months-claude-code-codex-sessions.md"}, "result": "# Five months of Claude Code and Codex usage analysed\nSource: https://x.com/quinn_leng/status/2085828592127336541\nMetrics: {\"sessions\": 8504, \"prs\": 1387, \"api_equivalent_cost\": \"~$56k API-priced usage\", \"period\": \"5 months\"}\n"}
{"turn": 2, "tool": "read_file", "args": {"path": "./sources/06-auto-job-applications.md"}, "result": "# Fill and submit job applications from a resume\nSource: https://x.com/SAkasxh/status/2104655629021565156\nMetrics: {\"applications\": 2, \"time\": \"about 18 seconds\", \"cost\": \"less than a fifth of a cent\"}\n"}
{"turn": 2, "tool": "read_file", "args": {"path": "./sources/10-agents-run-notetaker-startup.md"}, "result": "# Let agents run growth for a meeting-notetaker app\nSource: https://x.com/janaksunil/status/2105722379116933574\nMetrics: {\"ad_spend_managed\": \"$10,000\", \"users_acquired\": 1200, \"meeting_hours_collected\": 1500, \"duration\": \"2 months\"}\n"}
{"turn": 2, "tool": "read_file", "args": {"path": "./sources/15-ecommerce-tasks-cost-comparison.md"}, "result": "# 107 e-commerce tasks: Accio vs Codex vs Claude Code cost\nSource: https://x.com/dee_naliaks/status/2097947201066729536\nMetrics: {\"tasks\": 107, \"accio_cost\": \"about $3.69\", \"codex_cost\": \"about $9.27\", \"claude_code_cost\": \"about $9.51\"}\n"}
{"turn": 2, "tool": "read_file", "args": {"path": "./sources/20-flight-search-bakeoff.md"}, "result": "# Agent bake-off: find a premium flight home\nSource: https://x.com/twid/status/2101789185598247390\nMetrics: {\"result\": \"First place: Grok Bot\"}\n"}
{"turn": 2, "tool": "read_file", "args": {"path": "./sources/24-browser-agents-workday-test.md"}, "result": "# Test AI browser agents on real workday tasks\nSource: https://agentusecases.ai (listing: 'Test AI browser agents on real workday tasks', natesnewsletter.substack.com)\nMetrics: {\"flight_booking_time\": \"16 minutes (one agent)\", \"calendar_time\": \"about 5 minutes (other agent)\"}\n"}
{"turn": 3, "response": {"id": "4d20b6d9-8a11-9ac2-b5c7-b800ca7cd264", "object": "chat.completion", "created": 1792023643, "model": "grok-4-3", "choices": [{"index": 0, "message": {"role": "assistant", "content": null, "refusal": null, "reasoning_content": "I have reviewed the frozen notes and am now selecting the five most compelling use cases.\n\n[encrypted reasoning omitted, 611 chars]", "reasoning_encrypted": true, "reasoning_details": [{"type": "reasoning.encrypted", "format": "xai-responses-v1", "index": 0, "id": "rs_4d20b6d9-8a11-9ac2-b5c7-b800ca7cd264", "data": "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"}], "tool_calls": [{"id": "call-ff517db5-bfb5-4975-b51d-f4144a240fad-7", "type": "function", "function": {"name": "write_file", "arguments": "{\"path\":\"./slides.md\",\"content\":\"# Real-World AI Model Rankings\\n## Evidence-Based Pitch for Investor\\n### A platform to rank AI models by proven use-case outcomes\\n\\n---\\n\\n## 5 Months of Production Coding\\n**Source:** https://x.com/quinn_leng/status/2085828592127336541\\n\\n- 8504 sessions across Claude Code and Codex\\n- Delivered 1387 PRs\\n- \\\"~$56k API-priced usage\\\" over 5 months\\n\\n---\\n\\n## Automated Job Applications\\n**Source:** https://x.com/SAkasxh/status/2104655629021565156\\n\\n- 2 applications completed\\n- \\\"about 18 seconds\\\" total time\\n- \\\"less than a fifth of a cent\\\" cost\\n\\n---\\n\\n## Agents Running a Notetaker Startup\\n**Source:** https://x.com/janaksunil/status/2105722379116933574\\n\\n- \\\"$10,000\\\" ad spend managed autonomously\\n- 1200 users acquired\\n- 1500 meeting hours collected in 2 months\\n\\n---\\n\\n## 107 E-commerce Task Cost Comparison\\n**Source:** https://x.com/dee_naliaks/status/2097947201066729536\\n\\n- 107 tasks executed across models\\n- Accio: \\\"about $3.69\\\"\\n- Codex: \\\"about $9.27\\\"\\n- Claude Code: \\\"about $9.51\\\"\\n\\n---\\n\\n## Browser Agents on Real Workday Tasks\\n**Source:** https://agentusecases.ai (listing: 'Test AI browser agents on real workday tasks', natesnewsletter.substack.com)\\n\\n- Flight booking completed in \\\"16 minutes (one agent)\\\"\\n- Calendar task completed in \\\"about 5 minutes (other agent)\\\"\\n\\n---\\n\\n## Ask & Next Steps\\n- Seed round to build the live ranking platform\\n- Aggregate 50+ additional verified use-case notes in 90 days\\n- Launch public leaderboard + API for model selection\\n- Target: first paying enterprise subscribers within 6 months\\n\\n---\"}"}}]}, "finish_reason": "tool_calls", "logprobs": null}], "usage": {"prompt_tokens": 1480, "completion_tokens": 502, "total_tokens": 1982, "prompt_tokens_details": {"cached_tokens": 384}, "cache_read_input_tokens": 384, "completion_tokens_details": {"reasoning_tokens": 87}}, "cost": {"usd": 0, "diem": 0.0030652999999999995}, "venice_parameters": {"strip_thinking_response": false, "disable_thinking": false, "enable_e2ee": true, "enable_web_search": "off", "enable_web_scraping": false, "enable_web_citations": false, "include_search_results_in_stream": false, "include_venice_system_prompt": false, "enable_x_search": false, "web_search_citations": [], "return_search_results_as_documents": false}}}
{"turn": 3, "tool": "write_file", "args": {"path": "./slides.md", "content": "# Real-World AI Model Rankings\n## Evidence-Based Pitch for Investor\n### A platform to rank AI models by proven use-case outcomes\n\n---\n\n## 5 Months of Production Coding\n**Source:** https://x.com/quinn_leng/status/2085828592127336541\n\n- 8504 sessions across Claude Code and Codex\n- Delivered 1387 PRs\n- \"~$56k API-priced usage\" over 5 months\n\n---\n\n## Automated Job Applications\n**Source:** https://x.com/SAkasxh/status/2104655629021565156\n\n- 2 applications completed\n- \"about 18 seconds\" total time\n- \"less than a fifth of a cent\" cost\n\n---\n\n## Agents Running a Notetaker Startup\n**Source:** https://x.com/janaksunil/status/2105722379116933574\n\n- \"$10,000\" ad spend managed autonomously\n- 1200 users acquired\n- 1500 meeting hours collected in 2 months\n\n---\n\n## 107 E-commerce Task Cost Comparison\n**Source:** https://x.com/dee_naliaks/status/2097947201066729536\n\n- 107 tasks executed across models\n- Accio: \"about $3.69\"\n- Codex: \"about $9.27\"\n- Claude Code: \"about $9.51\"\n\n---\n\n## Browser Agents on Real Workday Tasks\n**Source:** https://agentusecases.ai (listing: 'Test AI browser agents on real workday tasks', natesnewsletter.substack.com)\n\n- Flight booking completed in \"16 minutes (one agent)\"\n- Calendar task completed in \"about 5 minutes (other agent)\"\n\n---\n\n## Ask & Next Steps\n- Seed round to build the live ranking platform\n- Aggregate 50+ additional verified use-case notes in 90 days\n- Launch public leaderboard + API for model selection\n- Target: first paying enterprise subscribers within 6 months\n\n---"}, "result": "wrote 1515 chars"}
{"turn": 4, "response": {"id": "240782e7-6ede-9919-a2ad-38de065dce9f", "object": "chat.completion", "created": 1792023649, "model": "grok-4-3", "choices": [{"index": 0, "message": {"role": "assistant", "content": "**slides.md created with 7 slides covering the 5 strongest use cases (coding volume, job apps, startup growth, e-comm cost bake-off, browser agents) plus title/ask.**", "refusal": null, "reasoning_content": "[encrypted reasoning omitted, 317 chars]", "reasoning_encrypted": true, "reasoning_details": [{"type": "reasoning.encrypted", "format": "xai-responses-v1", "index": 0, "id": "rs_240782e7-6ede-9919-a2ad-38de065dce9f", "data": "5w42eMau1Baua4bCl83U2yZkJlHrEWwr754MmkxPyKDnC8hmuV23LDNEvoupTeP3iGIYtpAIC4RG3d9jwnDwZfhlfypZpWQzDgibzSi+6UZIGAfTZrXCuSzzstZRz57Vi2eP4wNZL/q6UPTx2wbT/jB+Df/ADiTSFcDnON/WMQvdrO5KpER2tqN6YffK5QE+ygV3UijxUgdSDwfYfYxGqv+oZDf62ImG7FKLNZhnJm7hNGN7LMUbOm2nlsQgsjGeKVvyjuf9LBb//v56+g0g+Uj7sqktDaeflbNxDw"}]}, "finish_reason": "stop", "logprobs": null}], "usage": {"prompt_tokens": 1906, "completion_tokens": 81, "total_tokens": 1987, "prompt_tokens_details": {"cached_tokens": 1408}, "cache_read_input_tokens": 1408, "completion_tokens_details": {"reasoning_tokens": 42}}, "cost": {"usd": 0, "diem": 0.00126023}, "venice_parameters": {"strip_thinking_response": false, "disable_thinking": false, "enable_e2ee": true, "enable_web_search": "off", "enable_web_scraping": false, "enable_web_citations": false, "include_search_results_in_stream": false, "include_venice_system_prompt": false, "enable_x_search": false, "web_search_citations": [], "return_search_results_as_documents": false}}}

Get new runs and ranking changes weekly