Spend less and ship more with your models.
Move work to more efficient frontier models without giving up quality. Lower your spend or get more done for the same budget.
saved per month
($410,768 per year)
Spend reduction45.6%
New annual spend$489,232
was $900,000
New cost per task$9.42
was $17.32
Get your team's estimate
*Modeled on CursorBench cost per task. Cost view reprices the same tasks. Tasks view keeps your budget fixed. Actual results depend on your workload.
CursorBench 3.2
The calculator reads costs directly from the graph and leaderboard below, shared with cursor.com/evals.
| Model | |||||
|---|---|---|---|---|---|
| 1 | Fable 5 Max | 70.5% | $17.32 | 103,525 | 72 |
| 2 | Opus 5 Max | 70.0% | $8.23 | 61,838 | 78 |
| 3 | Opus 5 Extra High | 69.3% | $7.35 | 54,239 | 72 |
| 4 | Fable 5 Extra High | 68.4% | $11.73 | 64,971 | 56 |
| 5 | GPT-5.6 Sol Max | 67.2% | $5.69 | 28,320 | 48 |
| 6 | Opus 5 High | 66.7% | $3.91 | 27,932 | 48 |
| 7 | Grok 4.5 High* | 66.7% | $1.51 | 19,521 | 33 |
| 8 | Fable 5 High | 66.5% | $8.77 | 43,747 | 48 |
| 9 | Grok 4.5 Medium* | 65.4% | $1.54 | 18,914 | 34 |
| 10 | Fable 5 Medium | 65.2% | $6.80 | 30,366 | 41 |
| 11 | GPT-5.6 Terra Max | 64.9% | $2.31 | 32,969 | 47 |
| 12 | GPT-5.6 Sol Extra High | 64.5% | $3.88 | 19,699 | 38 |
| 13 | Opus 5 Medium | 64.3% | $3.29 | 23,612 | 44 |
| 14 | Grok 4.5 Low* | 63.5% | $1.22 | 15,841 | 31 |
| 15 | GPT-5.6 Sol High | 63.5% | $2.79 | 13,867 | 32 |
| 16 | Opus 5 Low | 62.8% | $2.55 | 18,529 | 37 |
| 17 | Opus 4.8 Max | 62.3% | $5.77 | 71,411 | 44 |
| 18 | Fable 5 Low | 62.1% | $4.46 | 18,182 | 31 |
| 19 | Sonnet 5 Max | 61.5% | $6.45 | 92,882 | 86 |
| 20 | GPT-5.6 Luna Max | 61.1% | $0.39 | 87,973 | 61 |
| 21 | Kimi K3 Max | 60.8% | $2.70 | 38,428 | 57 |
| 22 | GPT-5.6 Sol Medium | 60.0% | $1.95 | 9,747 | 27 |
| 23 | Kimi K3 High | 59.7% | $1.89 | 26,846 | 47 |
| 24 | Opus 4.8 Extra High | 59.4% | $4.50 | 51,121 | 40 |
| 25 | GPT-5.6 Terra Extra High | 59.2% | $1.15 | 16,089 | 29 |
| 26 | Sonnet 5 Extra High | 58.7% | $4.16 | 52,871 | 67 |
| 27 | GPT-5.5 High | 58.4% | $2.05 | 12,183 | 28 |
| 28 | GPT-5.5 Extra High | 58.4% | $2.85 | 17,534 | 32 |
| 29 | Opus 4.8 High | 58.0% | $3.15 | 33,548 | 33 |
| 30 | GPT-5.6 Luna Extra High | 57.7% | $0.23 | 22,480 | 48 |
| 31 | Sonnet 5 High | 56.9% | $3.19 | 39,483 | 57 |
| 32 | GPT-5.6 Luna High | 56.8% | $0.16 | 15,141 | 40 |
| 33 | Opus 4.8 Medium | 56.1% | $2.81 | 28,384 | 32 |
| 34 | Composer 2.5 | 56.1% | $0.44 | 14,286 | 33 |
| 35 | GLM 5.2 Max | 55.0% | $1.76 | 35,946 | 58 |
| 36 | GPT-5.6 Terra High | 54.2% | $0.71 | 9,468 | 23 |
| 37 | GPT-5.5 Medium | 53.8% | $1.51 | 8,522 | 25 |
| 38 | Gemini 3.6 Flash High | 53.5% | $1.56 | 30,436 | 64 |
| 39 | Opus 4.8 Low | 53.1% | $2.02 | 19,624 | 27 |
| 40 | GPT-5.6 Sol Low | 52.6% | $1.01 | 5,104 | 19 |
| 41 | Sonnet 5 Medium | 52.4% | $2.16 | 26,200 | 46 |
| 42 | GLM 5.2 High | 51.5% | $1.19 | 21,829 | 49 |
| 43 | Gemini 3.6 Flash Medium | 51.2% | $1.48 | 28,511 | 62 |
| 44 | Kimi K3 Low | 50.5% | $0.99 | 13,007 | 33 |
| 45 | GPT-5.6 Terra Medium | 50.3% | $0.49 | 6,222 | 20 |
| 46 | Kimi K2.7 Code | 49.7% | $1.43 | 31,247 | 58 |
| 47 | Gemini 3.5 Flash | 48.8% | $2.20 | 46,702 | 77 |
| 48 | GPT-5.6 Luna Medium | 47.7% | $0.08 | 7,095 | 28 |
| 49 | Sonnet 5 Low | 47.7% | $1.30 | 16,269 | 33 |
| 50 | Gemini 3.6 Flash Low | 47.4% | $1.13 | 20,529 | 50 |
| 51 | GPT-5.6 Terra Low | 46.9% | $0.42 | 5,312 | 19 |
| 52 | GPT-5.5 Low | 46.6% | $0.98 | 5,168 | 20 |
| 53 | GPT-5.6 Luna Low | 37.6% | $0.03 | 3,209 | 17 |
Avg cost per task is computed by applying each model's published per-million-token pricing (input, cache read, cache write, and output) to the tokens it used on each task. Results are subject to variance. Small score differences may not be statistically meaningful.