Examenos

54.4% · raw 54.4 %

Headline · max effort · Own vendor

Source/record date: 2026-09-22

FrontierCode v1.1 Main; adaptive max effort per table default

54.6% · raw 54.6 %

Alternative · medium effort · Own vendor

Source/record date: 2026-09-22

Default/medium effort on FrontierCode v1.1 main (cost chart text)

47.3% · raw 47.3 %

Alternative · low effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 9061, "cost": 0.4036, "duration_min": 4.87, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

54.6% · raw 54.64 %

Alternative · medium effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 18519, "cost": 0.8016, "duration_min": 6.34, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

54% · raw 53.99 %

Alternative · high effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 26143, "cost": 1.0896, "duration_min": 7.2, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

51.4% · raw 51.42 %

Alternative · xhigh effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 60182, "cost": 2.2545, "duration_min": 11.21, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

54.4% · raw 54.43 %

Alternative · max effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 165811, "cost": 6.191, "duration_min": 25.01, "flagged_rate": 0.008}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

53.3% · raw 53.3 %

Headline · unknown effort · Own vendor

Source/record date: 2026-09-03

FrontierCode 1.1 Main; footnote 8

53.3% · raw 53.3 %

Alternative · unknown effort · Peer vendor

Source/record date: 2026-09-22

As reported by Anthropic Opus 5.5 announce | Demoted 2026-09-25: duplicate of headline from OpenAI GPT-6 Astra announce (openai.com/index/gpt-6-astra); vendor official preferred over Anthropic peer comparison table (rule a); same value.

52.1% · raw 52.1 %

Headline · xhigh effort · Own vendor

Source/record date: 2026-09-28

FrontierCode v1.1 Main best at xhigh; max scores lower (46.2): Max-effort code-review skill caused timeouts and out-of-scope penalties

46.2% · raw 46.2 %

Alternative · max effort · Own vendor

Source/record date: 2026-09-28

Max-effort score; below xhigh best of 52.1

46.2% · raw 46.2 %

Alternative · max effort · Own vendor

Source/record date: 2026-10-07

Anthropic Haiku 5.5 system card, p. 113. Cognition official revision 1.1; Main 100 tasks, five runs/task. Claude Code for Claude; Codex for GPT. Max-effort summary, distinct from best-effort leaderboard. Alternative evidence; existing headline/configuration retained. No averaging.

52.1% · raw 52.1 %

Alternative · xhigh effort · Own vendor

Source/record date: 2026-10-07

Anthropic Haiku 5.5 system card, p. 113. Best published Sonnet effort is xhigh; retain max result separately. Alternative evidence; existing headline/configuration retained. No averaging.

29.3% · raw 29.33 %

Alternative · low effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 6353, "cost": 0.194, "duration_min": 3.83, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

36.5% · raw 36.48 %

Alternative · medium effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 7597, "cost": 0.2365, "duration_min": 4.35, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

49.4% · raw 49.38 %

Alternative · high effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 13003, "cost": 0.4175, "duration_min": 5.94, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

52.1% · raw 52.09 %

Alternative · xhigh effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 47385, "cost": 1.5881, "duration_min": 12.61, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

46.2% · raw 46.21 %

Alternative · max effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 595651, "cost": 20.7818, "duration_min": 62.39, "flagged_rate": 0.0465}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

50.9% · raw 50.9 %

Alternative · unknown effort · Peer vendor

Source/record date: 2026-09-03

As reported in OpenAI GPT-6 Astra comparison table | Demoted 2026-09-25: duplicate of headline from Anthropic Claude Opus 5.5 announce (anthropic.com/claude-opus-5-5); model vendor's own (Anthropic) figure preferred over peer-vendor OpenAI comparison table (rule a); Anthropic source is also later-dated (2026-09-22). Values differ (50.9 here vs 50.3 Anthropic); not reconciled.

50.3% · raw 50.3 %

Headline · unknown effort · Peer vendor

Source/record date: 2026-09-22

As reported by Anthropic Opus 5.5 announce

49.8% · raw 49.82 %

Alternative · low effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 19072.6, "cost": 2.3849, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

50.9% · raw 50.91 %

Alternative · medium effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 26109.6, "cost": 3.2845, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

50.3% · raw 50.34 %

Alternative · high effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 39918.6, "cost": 5.2741, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

48.7% · raw 48.73 %

Alternative · xhigh effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 67707.6, "cost": 9.2738, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

50.3% · raw 50.28 %

Alternative · max effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 91731.2, "cost": 12.8257, "flagged_rate": 0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

47.6% · raw 47.6 %

Headline · unknown effort · Own vendor

Source/record date: 2026-09-21

Cognition FrontierCode 1.1 Main leaderboard JSON-LD ItemList: Grok 4.7 Score 47.6% (added Sep 21, 2026 changelog)

46.4% · raw 46.4 %

Headline · max effort · Own vendor

Source/record date: 2026-10-07

Anthropic Haiku 5.5 system card, p. 113. Cognition official revision 1.1; Main 100 tasks, five runs/task. Claude Code for Claude; Codex for GPT. Max-effort summary, distinct from best-effort leaderboard.

45.8% · raw 45.8 %

Alternative · xhigh effort · Own vendor

Source/record date: 2026-10-07

Anthropic Haiku 5.5 system card, p. 111. Explicit xhigh score in summary table. Alternative evidence; existing headline/configuration retained. No averaging.

34.8% · raw 34.76 %

Alternative · low effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 23868, "cost": 0.0596, "duration_min": 6.71, "flagged_rate": null}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

41.6% · raw 41.63 %

Alternative · medium effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 36172, "cost": 0.13, "duration_min": 8.67, "flagged_rate": null}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

41.9% · raw 41.89 %

Alternative · high effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 55149, "cost": 0.256, "duration_min": 11.06, "flagged_rate": null}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

45.8% · raw 45.83 %

Alternative · xhigh effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 100847, "cost": 0.6297, "duration_min": 16.0, "flagged_rate": null}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

46.4% · raw 46.36 %

Alternative · max effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: claude-code. {"tokens": 181387, "cost": 1.3284, "duration_min": 23.55, "flagged_rate": null}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

43.6% · raw 43.6 %

Headline · unknown effort · Peer vendor

Source/record date: 2026-09-03

As reported in OpenAI GPT-6 Astra table

42.4% · raw 42.4 %

Headline · max effort · Peer vendor

Source/record date: 2026-10-07

Anthropic Haiku 5.5 system card, p. 113. Cognition official revision 1.1; Main 100 tasks, five runs/task. Claude Code for Claude; Codex for GPT. Max-effort summary, distinct from best-effort leaderboard.

25.7% · raw 25.66 %

Alternative · low effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: codex. {"tokens": 7325.0, "cost": 0.0199, "flagged_rate": 0.0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

35.5% · raw 35.53 %

Alternative · medium effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: codex. {"tokens": 21248.0, "cost": 0.0512, "flagged_rate": 0.0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

37.3% · raw 37.26 %

Alternative · high effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: codex. {"tokens": 28999.0, "cost": 0.0646, "flagged_rate": 0.002}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

37.1% · raw 37.1 %

Alternative · xhigh effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: codex. {"tokens": 33153.0, "cost": 0.07, "flagged_rate": 0.0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

42.4% · raw 42.42 %

Alternative · max effort · Own vendor

Source/record date: 2026-10-07

Cognition primary public data.json, v1_1 weighted new_score ×100, not unweighted correct. Harness: codex. {"tokens": 56553.0, "cost": 0.1027, "flagged_rate": 0.0}. Cost is source-observed USD/task; not an API rate. Data checked 8 October; evaluation date unpublished. Anthropic launch headline retained; exact board precision/effort alternative, no averaging.

41.3% · raw 41.3 %

Headline · unknown effort · Own vendor

Source/record date: 2026-08-01

Cognition FrontierCode 1.1 Main weighted score 41.3%; board export mirrored by evals.report (sourceUrl cognition.com) and matches llm-stats 0.413; Cognition changelog notes Terra/Luna pricing updates

40.1% · raw 40.1 %

Headline · unknown effort · Own vendor

Source/record date: 2026-09-02

Cognition FrontierCode 1.1 Main weighted score; model added Sep 2, 2026 per Cognition changelog; score 40.1% on board export mirrored by evals.report (sourceUrl cognition.com, verifiedStatus official, snapshot 2026-09-07)

31.8% · raw 31.8 %

Headline · unknown effort · Own vendor

Source/record date: 2026-09-02

Cognition FrontierCode 1.1 Main weighted score; model added Sep 2, 2026 per Cognition changelog; score 31.8% on board export mirrored by evals.report (sourceUrl cognition.com, verifiedStatus official, snapshot 2026-09-07)