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
Muse Spark 1.1
79 value index
Lowest price
$0.063
Granite 4.1 8b
Fastest TTFT
0.43s
Granite 4.1 8b
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 | 79value index | $2.00blended / 1M tokens | 0.83stime to first token | 113 tok/soutput speed | 81quality signal | ArenaArtificial Analysis | |
| #2 | 78value index | $6.00blended / 1M tokens | 1.36stime to first token | 63 tok/soutput speed | 87quality signal | ArenaArtificial Analysis | |
| #3 | 74value index | $10.00blended / 1M tokens | 1.61stime to first token | 45 tok/soutput speed | 87quality signal | ArenaArtificial Analysis | |
| #4 | 74value index | $3.38blended / 1M tokens | 0.77stime to first token | 232 tok/soutput speed | 71quality signal | ArenaArtificial Analysis | |
| #5 | 74value index | $10.00blended / 1M tokens | 11.5stime to first token | 46 tok/soutput speed | 88quality signal | ArenaArtificial Analysis | |
| #6 | 74value index | $4.50blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 67quality signal | ArenaArtificial Analysis | |
| #7 | 73value index | $10.00blended / 1M tokens | 1.82stime to first token | 43 tok/soutput speed | 85quality signal | ArenaArtificial Analysis | |
| #8 | 71value index | $3.16blended / 1M tokens | 0.95stime to first token | 81 tok/soutput speed | 69quality signal | ArenaArtificial Analysis | |
| #9 | 71value index | $3.38blended / 1M tokens | 10.6stime to first token | 268 tok/soutput speed | 67quality signal | ArenaArtificial Analysis | |
| #10 | 71value index | $2.15blended / 1M tokens | 1.01stime to first token | 62 tok/soutput speed | 66quality signal | ArenaArtificial Analysis | |
| #11 | 70value index | $11.25blended / 1M tokens | 2.50stime to first token | 60 tok/soutput speed | 82quality signal | ArenaArtificial Analysis | |
| #12 | 70value index | $1.71blended / 1M tokens | 1.16stime to first token | 46 tok/soutput speed | 64quality signal | ArenaArtificial Analysis | |
| #13 | 69value index | $3.75blended / 1M tokens | 1.54stime to first token | 202 tok/soutput speed | 64quality signal | ArenaArtificial Analysis | |
| #14 | 69value index | $4.00blended / 1M tokens | 1.52stime to first token | 62 tok/soutput speed | 66quality signal | ArenaArtificial Analysis | |
| #15 | 68value index | $3.00blended / 1M tokens | 13.4stime to first token | 73 tok/soutput speed | 65quality signal | ArenaArtificial Analysis | |
| #16 | 68value index | $0.544blended / 1M tokens | 2.21stime to first token | 63 tok/soutput speed | 58quality signal | ArenaArtificial Analysis | |
| #17 | 68value index | $4.50blended / 1M tokens | 23.7stime to first token | 126 tok/soutput speed | 67quality signal | ArenaArtificial Analysis | |
| #18 | 67value index | $1.71blended / 1M tokens | 1.08stime to first token | 52 tok/soutput speed | 59quality signal | ArenaArtificial Analysis | |
| #19 | 66value index | $20.00blended / 1M tokens | 55.9stime to first token | 58 tok/soutput speed | 98quality signal | ArenaArtificial Analysis | |
| #20 | 66value index | $10.00blended / 1M tokens | 21.8stime to first token | 55 tok/soutput speed | 75quality signal | ArenaArtificial Analysis | |
| #21 | 66value index | $6.00blended / 1M tokens | 47.9stime to first token | 58 tok/soutput speed | 71quality signal | ArenaArtificial Analysis | |
| #22 | 66value index | $0.700blended / 1M tokens | 1.62stime to first token | 53 tok/soutput speed | 54quality signal | ArenaArtificial Analysis | |
| #23 | 65value index | $11.25blended / 1M tokens | 12.5stime to first token | 69 tok/soutput speed | 74quality signal | ArenaArtificial Analysis | |
| #24 | 65value index | $1.13blended / 1M tokens | 0.70stime to first token | 212 tok/soutput speed | 51quality signal | ArenaArtificial Analysis | |
| #25 | 65value index | $0.544blended / 1M tokens | 0.95stime to first token | 63 tok/soutput speed | 52quality signal | ArenaArtificial Analysis | |
| #26 | 65value index | $0.544blended / 1M tokens | 0.95stime to first token | 60 tok/soutput speed | 52quality signal | ArenaArtificial Analysis | |
| #27 | 65value index | $0.525blended / 1M tokens | 1.16stime to first token | 55 tok/soutput speed | 52quality signal | ArenaArtificial Analysis | |
| #28 | 64value index | $0.525blended / 1M tokens | 1.14stime to first token | 74 tok/soutput speed | 51quality signal | ArenaArtificial Analysis | |
| #29 | 64value index | $2.93blended / 1M tokens | 2.15stime to first token | 39 tok/soutput speed | 56quality signal | ArenaArtificial Analysis | |
| #30 | 64value index | $1.10blended / 1M tokens | 1.08stime to first token | 149 tok/soutput speed | 50quality 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.
