docs(benchmark): simplify Claude-understated note to 'non-native unstable API'

Drop the bridge/CLI wording from the understated caveat in README, leaderboard and chart
caption — it now just says the Claude models ran through a non-native, unstable API with a high
tool-failure rate, so their scores are a lower bound. Chart subtitle updated to match.

Author: NeoXider

Docs/BENCHMARK_LEADERBOARD.md

@@ -53,10 +53,10 @@ CLIs). Ranked by suite base score. Per-group scores are G1…G8; see the benchma
 > fails" on the agentic Claude CLI. The remaining rows (sol, terra, gpt-5.5, luna, sonnet) predate that fix
 > and would likely gain a few points on a re-run.
 >
-> ⚠️ **Claude scores are understated.** The Claude models ran over the CLI bridge, not a native API, and
-> behaved unstably there — a high tool-failure rate (opus ~24%, sonnet ~23%, fable ~36%, where well-formed
-> tool calls still fail to land) that cost points on tool correctness and task completion. Treat the Claude
-> rows as a **lower bound** on their real capability; a native-API run would score higher.
+> ⚠️ **Claude scores are understated.** The Claude models ran through a non-native, unstable API that gave
+> them a high tool-failure rate (opus ~24%, sonnet ~23%, fable ~36%, where well-formed tool calls still fail
+> to land) — costing points on tool correctness and task completion. Treat the Claude rows as a **lower
+> bound** on their real capability; a native API run would score higher.
 
 ## Historical Leaderboard — Suite v1.6
 

Docs/Images/benchmark_v2_frontier.md

@@ -19,10 +19,10 @@
 > `opus-4.8`, `fable-5` and `gpt-5.3-spark` were re-run after the `cli-agents` bridge gained a
 > no-tool-call recovery retry. Single run per model over the CLI bridge; speed is reported, never scored.
 >
-> ⚠️ **Claude scores are understated.** The Claude rows were driven over the CLI bridge, where a high
-> tool-failure rate (opus ~24%, sonnet ~23%, fable ~36% — well-formed calls that still fail to land)
-> cost points on tool correctness and task completion. Read them as a lower bound; a native-API run
-> would score higher. See [BENCHMARK_LEADERBOARD.md](../BENCHMARK_LEADERBOARD.md) for the full per-group (G1…G8) table.
+> ⚠️ **Claude scores are understated.** The Claude rows ran through a non-native, unstable API with a high
+> tool-failure rate (opus ~24%, sonnet ~23%, fable ~36% — well-formed calls that still fail to land) that
+> cost points on tool correctness and task completion. Read them as a lower bound; a native API run would
+> score higher. See [BENCHMARK_LEADERBOARD.md](../BENCHMARK_LEADERBOARD.md) for the full per-group (G1…G8) table.
 
 ```mermaid
 xychart-beta

Docs/Images/benchmark_v2_frontier.png

@@ -104,12 +104,11 @@ CoreAI ships a game-creation benchmark: it scores how well an LLM builds and cha
 
 One run each via the `cli-agents` bridge (indicative).
 
-> ⚠️ **Claude scores are understated.** The Claude models (`sonnet-5`, `opus-4.8`, `fable-5`) were driven
-> over the `cli-agents` CLI bridge, not a native API. On that bridge they behaved unstably — a high
-> tool-failure rate (opus ~24%, sonnet ~23%, fable ~36% vs 1–13% for the Codex models) where
-> well-formed tool calls still failed to land. Those failures cost points on tool correctness and task
-> completion, so the Claude rows sit a few points below their true capability. Read them as a **lower
-> bound**, not a ceiling — a native-API run would score higher.
+> ⚠️ **Claude scores are understated.** The Claude models (`sonnet-5`, `opus-4.8`, `fable-5`) ran through
+> a non-native, unstable API that gave them a high tool-failure rate (opus ~24%, sonnet ~23%, fable ~36%
+> vs 1–13% for the Codex models) — well-formed tool calls that still failed to land. Those failures cost
+> points on tool correctness and task completion, so the Claude rows sit a few points below their true
+> capability. Read them as a **lower bound**, not a ceiling — a native API run would score higher.
 
 Full tables (v2 + historical + local), methodology, group legend and the per-model castle prefabs: **[benchmark guide](Assets/CoreAIBenchmark/README.md)** · **[leaderboard](Docs/BENCHMARK_LEADERBOARD.md)**.