Model value rankings.
A focused view of which frontier models deliver the strongest benchmark signal for the money, balancing quality, blended token price, latency, and output speed.
Ranked models
92
Require quality and price matches
Best value
Gemini 3.7 Flash High
84 value index
Lowest price
$0.100
Hy3
Fastest TTFT
0.40s
Muse Glimmer
Value formula
Quality first, then cost and speed.
The value index normalizes each available signal before blending benchmark quality, blended price, time to first token, and output speed. It avoids raw score-per-dollar math, which can wildly overstate very cheap models.
Best models for the money
Higher value index is better. Missing source rows are omitted from the value ranking rather than treated as zero.
Top 30 of 92
| Rank | Model | Index | Price | Latency | Speed | Quality | Sources |
|---|---|---|---|---|---|---|---|
| #1 | 84value index | $1.50blended / 1M tokens | 5.40stime to first token | 286 tok/soutput speed | 76quality signal | ArenaArtificial Analysis | |
| #2 | 81value index | $0.230blended / 1M tokens | 1.27stime to first token | 84 tok/soutput speed | 81quality signal | ArenaArtificial Analysis | |
| #3 | 81value index | $2.00blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 74quality signal | ArenaArtificial Analysis | |
| #4 | 80value index | $10.00blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 87quality signal | ArenaArtificial Analysis | |
| #5 | 78value index | $3.00blended / 1M tokens | 1.41stime to first token | 40 tok/soutput speed | 83quality signal | ArenaArtificial Analysis | |
| #6 | 76value index | $10.00blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 81quality signal | ArenaArtificial Analysis | |
| #7 | 76value index | $10.00blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 81quality signal | ArenaArtificial Analysis | |
| #8 | 75value index | $1.50blended / 1M tokens | 12.9stime to first token | 161 tok/soutput speed | 69quality signal | ArenaArtificial Analysis | |
| #9 | 74value index | $0.237blended / 1M tokens | 1.43stime to first token | 42 tok/soutput speed | 70quality signal | ArenaArtificial Analysis | |
| #10 | 74value index | $3.38blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 65quality signal | ArenaArtificial Analysis | |
| #11 | 73value index | $10.00blended / 1M tokens | 6.71stime to first token | 47 tok/soutput speed | 86quality signal | ArenaArtificial Analysis | |
| #12 | 73value index | $2.00blended / 1M tokens | 33.3stime to first token | 77 tok/soutput speed | 79quality signal | ArenaArtificial Analysis | |
| #13 | 72value index | $3.38blended / 1M tokens | 9.01stime to first token | 232 tok/soutput speed | 61quality signal | ArenaArtificial Analysis | |
| #14 | 71value index | $8.00blended / 1M tokens | 16.2stime to first token | 76 tok/soutput speed | 81quality signal | ArenaArtificial Analysis | |
| #15 | 71value index | $0.850blended / 1M tokens | 7.18stime to first token | 322 tok/soutput speed | 47quality signal | ArenaArtificial Analysis | |
| #16 | 70value index | $6.00blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 64quality signal | ArenaArtificial Analysis | |
| #17 | 69value index | $3.75blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 59quality signal | ArenaArtificial Analysis | |
| #18 | 69value index | $4.50blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 60quality signal | ArenaArtificial Analysis | |
| #19 | 67value index | $3.00blended / 1M tokens | 11.5stime to first token | 48 tok/soutput speed | 65quality signal | ArenaArtificial Analysis | |
| #20 | 67value index | $10.00blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 68quality signal | ArenaArtificial Analysis | |
| #21 | 67value index | $4.50blended / 1M tokens | 2.56stime to first token | 87 tok/soutput speed | 62quality signal | ArenaArtificial Analysis | |
| #22 | 67value index | $0.450blended / 1M tokens | 2.33stime to first token | 110 tok/soutput speed | 52quality signal | ArenaArtificial Analysis | |
| #23 | 67value index | $4.00blended / 1M tokens | 1.34stime to first token | 60 tok/soutput speed | 61quality signal | ArenaArtificial Analysis | |
| #24 | 67value index | $1.71blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 52quality signal | ArenaArtificial Analysis | |
| #25 | 66value index | $11.25blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 67quality signal | ArenaArtificial Analysis | |
| #26 | 65value index | $2.14blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 50quality signal | ArenaArtificial Analysis | |
| #27 | 64value index | $4.50blended / 1M tokens | 24.6stime to first token | 113 tok/soutput speed | 61quality signal | ArenaArtificial Analysis | |
| #28 | 64value index | $0.700blended / 1M tokens | 1.42stime to first token | 56 tok/soutput speed | 49quality signal | ArenaArtificial Analysis | |
| #29 | 63value index | $11.25blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 63quality signal | ArenaArtificial Analysis | |
| #30 | 63value index | $5.63blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 53quality signal | ArenaArtificial Analysis |
Benchmark guide
What the scores mean.
A quick reading key for interpreting the value rankings without over-weighting one benchmark, price point, or speed measurement.
What does the value index measure?
The value index blends normalized benchmark quality, blended token price, latency, and output speed. It is designed to answer which models deliver strong public performance for the money, not which model is best in every task.
Why not use raw score divided by price?
Raw score-per-dollar can exaggerate extremely cheap models and make small benchmark differences look larger than they are. Normalizing each signal keeps the ranking easier to compare across quality, price, and speed.
Why are some models missing from value rankings?
A model needs both a benchmark quality signal and a confident price match to be ranked. If the price or benchmark source is missing, the model is omitted rather than treated as free or zero quality.
How should I use price, latency, and speed together?
Price estimates cost, latency measures time to first token, and speed measures output throughput after generation begins. The best model for a product depends on which constraint matters most in the actual workflow.
