com.modevc/chart-open-source-vs-closed-ai-models-gap
Mode VC Chart: Open-Source vs. Closed AI Models: How Big Is the Gap?
Is the Mode VC Chart MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-09.
The best open model trails the best closed model by 42 Arena points. In a blind vote it would.
alive probed 2026-11-15 · unchanged since 2026-11-09 · HTTP 200
- Endpoint
- https://modevc.com/api/mcp/chart-open-source-vs-closed-ai-models-gap (streamable-http)
- Host
- modevc.com
- Protocol
- 2025-11-25
- Reports itself as
- com.modevc/radar 2.1.0
- Capabilities
- resources, tools
- Instructions
- 1 119 characters
- Of a 1M window
- 1.2 % of a 1M context window
- Count
- 12k tokens in Claude, exact, measured 2026-11-09. With the Claude Code prefix mcp__…__ on each tool name: 12k. The o200k_base estimate is 6.8k. Counted again when the tool definitions change. Method.
- Website
- https://modevc.com/charts/open-source-vs-closed-ai-models-gap/
- Registry
- active, updated 2026-10-18 · registry entry
- Changes
- 5 recorded, reachable in 5 of them. A row is added when the result, the tool count or the cost changes.
Most expensive tools
The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.73×.
| Tool | ≈ Claude tokens | o200k estimate | Share of this server |
|---|---|---|---|
| calc_llm_inference_cost | 1 291 | 748 | 11 % |
| calc_83b_qsbs_delaware | 1 172 | 679 | 10 % |
| calc_cofounder_equity | 994 | 576 | 9 % |
| calc_safe_dilution | 961 | 557 | 8 % |
| calc_saas_metrics | 810 | 469 | 7 % |
Compare this server with others, or with the servers that share its tool set.
Same tool set as 83 other servers
These registry entries have the same tool names and the same schema sizes.
- com.modevc/chart-ai-adoption-rate-us-businesses modevc.com
- com.modevc/chart-ai-chatbot-adoption-by-age-demographics modevc.com
- com.modevc/chart-ai-coding-assistant-statistics modevc.com
- com.modevc/chart-ai-in-the-workplace-statistics modevc.com
- com.modevc/chart-ai-inference-cost-comparison modevc.com
- com.modevc/chart-ai-model-launch-strategy modevc.com
- com.modevc/chart-ai-model-releases-2026 modevc.com
- com.modevc/chart-ai-productivity-statistics modevc.com
- com.modevc/chart-anthropic-sdk-vs-openai-sdk-npm-downloads modevc.com
- com.modevc/chart-anthropic-vs-openai-vs-google-arena-top-20 modevc.com
- com.modevc/chart-arena-rating-gap-google-anthropic-openai modevc.com
- com.modevc/chart-best-ai-for-creative-writing modevc.com
- and 71 more
More servers
Other registry entries on modevc.com, the ones next to this name; all of them.
- Mode VC Chart: LLM Leaderboard Top 10: #1 Leads #10 by 18 Points com.modevc/chart-llm-leaderboard-top-10-gap · alive
- Mode VC Chart: LLM Rankings by Category: The Hidden Specialists com.modevc/chart-llm-rankings-by-category-specialists · alive
- Mode VC Chart: MCP Adoption: Model Context Protocol SDK Downloads com.modevc/chart-mcp-adoption-model-context-protocol-downloads · alive
- Mode VC Chart: Ollama Downloads: Is Local LLM Adoption Keeping Up? com.modevc/chart-ollama-downloads-local-llm-adoption · alive
- Mode VC Chart: Open-Weight Models in 2026: How Many Launch Open? com.modevc/chart-open-weight-models-2026 · alive
- Mode VC Chart: Open Weights vs. Proprietary AI: The Gap Stays at 42 Points com.modevc/chart-open-weights-vs-proprietary-arena-gap · alive
- Mode VC Chart: OpenAI Leaderboard Ranking: 8th Among Labs on Arena com.modevc/chart-openai-leaderboard-ranking · alive
- Mode VC Chart: OpenAI Python Package Downloads: Who Grew Since August com.modevc/chart-openai-python-package-downloads-pypi-growth · alive
Servers that mention closed.
- WEM Price Compare ai.wem3/wem-price-compare · alive
- com.alphaassay/mcp · alive
- CEF Radar com.cefradar/cefradar · alive
- disclosedby, the subprocessor record com.disclosedby/record · alive
- Do Not Act com.donotact/donotact · refused
- com.edgethirteen.www/tariff-refund-screen · not found
- Power Expert India Regulatory Tariff MCP com.powerexpertindia/tariff-mcp · needs auth
- RQM Studio Jobs com.rqmtechnologies/studio · alive
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-11-09 11:49 | alive | 156 ms | 20 | 12k | 6.8k |
| 2026-11-06 11:08 | alive | 36 ms | 19 | 11k | 6.4k |
| 2026-10-25 20:26 | alive | 63 ms | 3 | 634 | 357 |
| 2026-10-21 09:47 | alive | 349 ms | 3 | 357 | |
| 2026-10-18 08:33 | alive | 164 ms | 3 | 323 |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The server answers initialize and tools/list. Nothing to fix.
Fixed something? Probe it now, with the same steps as the daily run. This page updates with the next daily run.