Janus Labs · Epoch 3

Leaderboard v2 — Quality × Cost

Every point is a model through a specific harness — the same model may appear once per CLI, because the scaffold measurably matters (native CLIs outscore the Copilot scaffold by 1.2–2.5 points on every pair tested). Token burn is captured where the agent CLI reports it. The v1 board is grandfathered, frozen as of 2026-07-11. Epoch 3 (current): suite v3 red-start guarantees, median of 3 runs per model/harness with min–max spread whiskers, and fail-to-act ("Acts") as a first-class metric. The epoch-2 board is grandfathered, frozen 2026-07-25.

FLAT-FEE 92 88 85 82 78 $0 $10 $20 $30 $40 $50 List output price, USD per MTok (priced 2026-08-02) · y-axis zoomed 78–92 GEval score VALUE FRONTIER PREMIUM TIER COMMODITY DEAD ZONE claude-opus-4-7 via claude — 87.66 (A) — $25.0/MTok out · acts 100% opus-4-7 87.7 claude-opus-4-8 via claude — 87.1 (A) — $25.0/MTok out · acts 100% opus-4-8 87.1 claude-haiku-4-5-20251001 via claude — 86.7 (A) — $5.0/MTok out · acts 100% haiku-4-5 86.7 claude-sonnet-4.6 via copilot — 86.61 (A) — subscription route · acts 100% sonnet-4.6 86.6 claude-opus-5 via copilot — 86.41 (A) — subscription route · acts 100% opus-5 86.4 claude-opus-4.8 via copilot — 85.86 (A) — subscription route · acts 100% opus-4.8 85.9 claude-sonnet-4-6 via claude — 85.79 (A) — $15.0/MTok out · acts 100% sonnet-4-6 85.8 claude-fable-5 via claude — 85.54 (A) — $50.0/MTok out · acts 100% fable-5 85.5 claude-opus-5 via claude — 85.53 (A) — $25.0/MTok out · acts 100% opus-5 85.5 claude-opus-4.7 via copilot — 85.41 (A) — subscription route · acts 100% opus-4.7 85.4 gpt-5.5 via copilot — 84.96 (B) — subscription route · acts 100% gpt-5.5 85.0 gpt-5.4 via copilot — 84.41 (B) — subscription route · acts 100% gpt-5.4 84.4 gemini-3.1-pro-preview via gemini — 84.15 (B) — $12.0/MTok out · acts 100% gemini-3.1-pro-preview 84.2 gpt-5.5 via codex — 83.7 (B) — $30.0/MTok out · acts 100% gpt-5.5 83.7 gpt-5.6-luna via codex — 82.03 (B) — $1.2/MTok out · acts 100% gpt-5.6-luna 82.0 gpt-5.6-sol via copilot — 81.99 (B) — subscription route · acts 100% gpt-5.6-sol 82.0 gpt-5.6-terra via codex — 80.84 (B) — $12.0/MTok out · acts 100% gpt-5.6-terra 80.8 gpt-5.6-sol via codex — 80.74 (B) — $30.0/MTok out · acts 100% gpt-5.6-sol 80.7 claude-sonnet-5 via claude — 80.53 (B) — $10.0/MTok out · acts 100% sonnet-5 80.5 gemini-2.5-pro via gemini — 78.8 (B) — $10.0/MTok out · acts 100% gemini-2.5-pro 78.8 gpt-5.3-codex via codex — 57.14 (C) — $14.0/MTok out · acts 75% gpt-5.3-codex 57.1
Anthropic model OpenAI model ◌ dashed ring — flat-fee via Copilot CLI (≈$0 marginal) solid dots — native CLI, metered API
#ModelHarnessRoute ScoreGradeActs Runs Time TokensCost (run)$/MTok out
1 claude-opus-4-7 claude api_key 87.7 A 100% 3 (86.7–87.9) 7.7m 1,709,928 $1.97 $25
2 claude-opus-4-8 claude api_key 87.1 A 100% 3 (86.2–87.7) 7.3m 815,937 $1.38 $25
3 claude-haiku-4-5-20251001 claude api_key 86.7 A 100% 3 (86.4–86.8) 7.0m 1,797,828 $0.44 $5
4 claude-sonnet-4.6 copilot subscription 86.6 A 100% 3 (86.3–86.8) 6.5m 930,100 flat-fee
5 claude-opus-5 copilot subscription 86.4 A 100% 3 (85.3–86.4) 7.7m 1,830,100 flat-fee
6 gemini-2.5-flash gemini api_key 85.9 A 100% 3 (75.7–86.9) 10.5m
7 claude-opus-4.8 copilot subscription 85.9 A 100% 3 (85.0–86.0) 6.6m 1,248,600 flat-fee
8 claude-sonnet-4-6 claude api_key 85.8 A 100% 3 (85.4–87.4) 7.7m 1,292,928 $0.98 $15
9 claude-fable-5 claude api_key 85.5 A 100% 3 (82.1–85.9) 7.2m 852,654 $2.71 $50
10 claude-opus-5 claude api_key 85.5 A 100% 3 (84.9–86.5) 11.3m 1,538,567 $2.63 $25
11 claude-opus-4.7 copilot subscription 85.4 A 100% 3 (85.2–86.9) 4.7m 1,145,800 flat-fee
12 gpt-5.5 copilot subscription 85.0 B 100% 3 (84.2–85.2) 9.2m 1,360,000 flat-fee
13 gpt-5.4 copilot subscription 84.4 B 100% 3 (84.3–87.7) 7.4m 1,164,900 flat-fee
14 gemini-3.1-pro-preview gemini api_key 84.2 B 100% 3 (75.1–87.0) 10.6m $12
15 gpt-5.5 codex api_key 83.7 B 100% 3 (83.5–85.2) 6.8m 920,552 $30
16 gpt-5.6-luna codex api_key 82.0 B 100% 3 (79.0–82.8) 3.7m 443,656 $0.10 $1
17 gpt-5.6-sol copilot subscription 82.0 B 100% 3 (81.4–86.4) 5.7m 836,100 flat-fee
18 gpt-5.6-terra codex api_key 80.8 B 100% 3 (80.6–81.6) 4.0m 439,184 $1.00 $12
19 gpt-5.6-sol codex api_key 80.7 B 100% 3 (80.2–86.4) 5.0m 560,471 $3.15 $30
20 claude-sonnet-5 claude api_key 80.5 B 100% 3 (80.1–81.7) 8.6m 1,744,759 $1.49 $10
21 gemini-2.0-flash gemini api_key 79.3 B 100% 3 (77.9–86.5) 12.9m
22 gemini-2.5-pro gemini api_key 78.8 B 100% 3 (70.1–81.1) 7.0m $10
23 gpt-5.3-codex codex api_key 57.1 C 75% 3 (43.7–72.2) 3.4m 357,962 $0.72 $14

Quality = GEval-blended score, refactor-storm suite v3.0.0 (red-start guarantees); median of up to 3 runs per model/harness, spread shown as whiskers. "Acts" = action reliability — the share of behaviors where the agent actually engaged the workspace (fail-to-act is a first-class metric). The same model may appear once per harness — the harness effect is measured, not deduplicated. Cost (run): measured where the CLI reports dollars (claude); † = derived from measured tokens × list per-MTok prices (codex). Gemini CLI reports neither tokens nor dollars, and Copilot bills in AI Credits (no USD conversion) — those rows show no run cost. Cost axis uses list output pricing as of 2026-08-02 until measured token burn covers the board.