AI Coding Benchmarks & Rankings
Empirical evaluations measuring coding intelligence, agentic task resolution, execution speed, and token cost economics across 30 frontier models.
Claude Sonnet 5.5
Claude Opus 5.5
Gemini 4 Argon (high)
| IN / OUT ($/1M) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 01 ▲+15 |
|
90.6% | 53.8% | 1M | 95 t/s TTFT 3820ms | $8.00 | $0.1413 | — | 2026-09-22 | $4.00 / $20.00 | |
| 02 ▼-1 |
|
93.0% | 50.5% | 1M | 136 t/s TTFT 1160ms | $4.00 | $0.0723 | — | 2026-09-28 | $2.00 / $10.00 | |
| 03 ▲+1 |
|
96.5% | 55.0% | 1.048576M | 83 t/s TTFT 2450ms | $4.00 | $0.0745 | — | 2026-10-13 | $2.00 / $10.00 | |
| 04 ▼-1 |
|
71.5% | 55.0% | 1.1M | 62 t/s TTFT 4100ms | $20.00 | $0.3763 | — | 2026-09-28 | $10.00 / $50.00 | |
| 05 ▼-4 |
|
72.0% | 54.6% | 1M | 68 t/s TTFT 2620ms | $30.00 | $0.5645 | — | 2026-09-15 | $15.00 / $75.00 | |
| 06 ▲+1 |
|
52.0% | 36.8% | 1M | 86 t/s TTFT 1750ms | $0.96 | $0.0267 | — | 2026-08-13 | $0.30 / $2.94 | |
| 07 ▲+1 |
|
49.0% | 34.6% | 128K | 178 t/s TTFT 850ms | $0.35 | $0.0103 | — | 2026-08-15 | $0.10 / $1.10 | |
| 08 ▲+1 |
|
44.5% | 30.2% | 2M | 112 t/s TTFT 1400ms | $1.40 | $0.0468 | — | 2026-06-15 | $0.50 / $4.10 | |
| 09 ▲+1 |
|
67.0% | 29.0% | 131.072K | 220 t/s TTFT 480ms | $0.21 | $0.0074 | — | 2026-10-13 | $0.05 / $0.70 | |
| 10 ▲+1 |
|
74.0% | 34.5% | 1M | 137 t/s TTFT 1200ms | $0.75 | — | — | 2026-10-14 | $0.50 / $1.50 | |
| 11 ▲+1 |
|
76.0% | 36.0% | 1M | 125 t/s TTFT 1250ms | $0.44 | — | — | 2026-10-16 | $0.25 / $1.00 | |
| 12 ▲+1 |
|
78.0% | 37.5% | 1M | 181 t/s TTFT 820ms | $0.26 | — | — | 2026-10-19 | $0.15 / $0.60 | |
| 13 ▲+1 |
|
80.5% | 39.0% | 1M | 210 t/s TTFT 550ms | $0.20 | — | — | 2026-10-07 | $0.10 / $0.50 | |
| 14 ▲+1 |
|
81.0% | 39.5% | 1.1M | 195 t/s TTFT 650ms | $0.20 | — | — | 2026-10-08 | $0.10 / $0.50 | |
| 15 ▲+1 |
|
79.5% | 40.2% | 1M | 490 t/s TTFT 420ms | $0.80 | — | — | 2026-10-07 | $0.20 / $2.60 | |
| 16 ▲+1 |
|
83.0% | 43.0% | 1.048576M | 115 t/s TTFT 1350ms | $2.00 | — | — | 2026-10-15 | $1.25 / $4.25 | |
| 17 ▲+1 |
|
84.0% | 43.5% | 1M | 186 t/s TTFT 850ms | $0.26 | — | — | 2026-10-17 | $0.15 / $0.60 | |
| 18 ▲+1 |
|
86.5% | 44.0% | 500K | 105 t/s TTFT 1500ms | $3.50 | — | — | 2026-09-30 | $2.00 / $8.00 | |
| 19 ▲+1 |
|
87.0% | 46.5% | 1M | 92 t/s TTFT 1650ms | $2.07 | — | — | 2026-10-06 | $1.36 / $4.18 | |
| 20 ▲+1 |
|
91.5% | 49.5% | 1.1M | 110 t/s TTFT 1450ms | $4.00 | — | — | 2026-10-08 | $2.00 / $10.00 | |
| 21 ▲+1 |
|
88.5% | 51.5% | 1.048576M | 88 t/s TTFT 2150ms | $8.00 | — | — | 2026-10-12 | $4.00 / $20.00 | |
| 22 ▼-12 |
|
35.5% | 23.2% | 1M | 298 t/s TTFT 380ms | $0.17 | — | — | 2026-06-01 | $0.05 / $0.53 | |
| 23 ▲+1 |
|
40.0% | 26.6% | 256K | 132 t/s TTFT 1100ms | $0.75 | — | — | 2026-07-01 | $0.25 / $2.25 | |
| 24 ▲+1 |
|
46.0% | 31.8% | 1M | 98 t/s TTFT 1600ms | $1.20 | — | — | 2026-09-01 | $0.40 / $3.60 | |
| 25 ▲+1 |
|
50.5% | 35.6% | 1M | 154 t/s TTFT 1050ms | $0.47 | — | — | 2026-08-25 | $0.20 / $1.28 | |
| 26 ▲+1 |
|
56.5% | 40.6% | 1M | 165 t/s TTFT 880ms | $0.45 | — | — | 2026-09-10 | $0.15 / $1.35 | |
| 27 ▼-21 |
|
58.0% | 41.8% | 1M | 145 t/s TTFT 950ms | $1.31 | — | — | 2026-08-20 | $0.40 / $4.04 | |
| 28 ▲+1 |
|
61.5% | 44.6% | 1M | 90 t/s TTFT 1800ms | $1.20 | — | — | 2026-10-01 | $0.40 / $3.60 | |
| 29 ▼-21 |
|
61.8% | 44.8% | 2M | 82 t/s TTFT 2100ms | $1.80 | — | — | 2026-07-20 | $0.60 / $5.40 | |
| 30 ▼-21 |
|
63.5% | 46.0% | 1M | 76 t/s TTFT 1950ms | $3.00 | — | — | 2026-09-02 | $1.20 / $8.40 |
Interactive Benchmark Visualizations
Explore head-to-head architectural comparisons across intelligence, inference speed, token pricing, and cost-efficiency sweet spots.
Initial multi-file coding and git diff generation baseline.
Standardization of SWE-bench Verified and tool-use agent harnesses.
Open weights models reach parity on competitive programming benchmarks.
Extended test-time compute, autonomous repository debugging, and 1M+ context reasoning.
6-Benchmark Performance Heatmap
| MODEL & PROVIDER | SWE-BENCH | TERMINAL 2.0 | LIVECODE | AIDER POLY | GPQA DIAMOND | SCICODE |
|---|---|---|---|---|---|---|
| 53.8% | 66.4% | 51.2% | 54.0% | 90.6% | 57.0% | |
| 50.5% | 70.6% | 47.0% | 52.0% | 93.0% | 54.0% | |
| 55.0% | 57.4% | 47.5% | 51.0% | 96.5% | 55.0% | |
| 55.0% | 51.5% | 50.5% | 53.5% | 71.5% | 57.5% | |
| 54.6% | 52.0% | 50.0% | 54.0% | 72.0% | 58.0% | |
| 36.8% | 35.5% | 33.5% | 37.0% | 52.0% | 38.0% | |
| 34.6% | 33.5% | 32.0% | 35.0% | 49.0% | 35.5% | |
| 30.2% | 30.2% | 27.5% | 30.8% | 44.5% | 31.0% | |
| 29.0% | 28.5% | 27.5% | 29.5% | 67.0% | 32.0% | |
| 34.5% | 34.0% | 32.5% | 35.0% | 74.0% | 36.5% | |
| 36.0% | 35.0% | 34.0% | 36.5% | 76.0% | 38.0% | |
| 37.5% | 37.0% | 35.5% | 38.0% | 78.0% | 40.0% | |
| 39.0% | 38.5% | 37.0% | 39.0% | 80.5% | 41.5% | |
| 39.5% | 38.8% | 37.5% | 39.5% | 81.0% | 42.0% | |
| 40.2% | 39.5% | 38.0% | 40.5% | 79.5% | 43.5% | |
| 43.0% | 42.0% | 41.0% | 43.5% | 83.0% | 47.0% |
Leaderboard Methodology & Evaluation Harness
Isolated Docker Execution
Every agentic benchmark (SWE-bench Verified and Terminal-Bench 2.0) is evaluated inside clean, network-isolated Docker containers with fixed system dependencies, preventing prompt leakage and external tool interference.
Zero-Data Fabrication Guarantee
We enforce strict provenance rules. Every number displayed originates from our verified in-house test harness (★) or vendor-published telemetry (†). Models awaiting re-test display "Not tested yet" rather than estimated values.
Normalized Blended Cost Formula
Blended cost per 1M tokens assumes an industry-standard 3:1 prompt to generation ratio ((3 × Input + 1 × Output) / 4). The Value Index ($/Point) measures total blended dollars required per index point scored.