INTELLIGENCE
16.9
Media Cap quality axis
Sarvam AI · Open weightsSarvam 105B
Active
Model portfolio
Sarvam 105B
Tap a star to rate
Sarvam AI · Released 2026-03-06 · v2026-03-06 · Open · Context 131K tokens
Language Cap
50
Cadle Language Cap 50 · 76%
Benchmark average
68.7
Not enough benchmark results yet
Pricing
$0.040
$0.16 / 1M out · 130.4 pts/$
CADLE CAP vs MODEL MATRIX
Cadle Cap ranks models on every published score we have for them — harder benchmarks weigh more. Missing tests are skipped, not zeroed. It answers who is stronger than whom in today's pool.
Model Matrix is the datasheet: Overall, Intelligence, Coding, Agentic, MMLU, GPQA, Math, LiveCodeBench, HumanEval, Reason, ARC-AGI. A dash means unmeasured. AVG is an importance-weighted mean of that model's filled cells only.
MODEL MATRIX · TRUTH CENTER CELLS
Overall
31.6
Intelligence
8.8
Coding
45.0
Agentic
48.1
MMLU
93.4
GPQA
73.8
Math
98.6
LiveCodeBench
No data yet
HumanEval
No data yet
Reason
59.6
ARC-AGI
No data yet
Coverage AVG
68.7
Cadle Cap ranks models with within-benchmark percentiles so ARC-AGI ~40 and MMLU ~90 never compete raw. Coverage AVG is an importance-weighted mean of filled expert cells only — blanks are skipped, not zeroed.
ANALYSIS · TRUTH CENTER
Hard benches (GPQA · ARC-AGI · LCB · Agentic) sit left — a mid-40 on ARC-AGI can still be frontier. Broader benches on the right are easier and often higher.
CADLE INSIGHTS
Only measured signals
CODING
45.0
Media Cap quality axis
AGENTIC
48.1
Media Cap quality axis
MATH
98.6
Media Cap quality axis
MATRIX OVERALL
31.6
AVG 68.7 across matrix cells
STRONGEST SIGNAL
Intelligence
Cap axis 16.9
BLENDED $/1M
$0.20
In $0.040 · Out $0.16
VALUE INDEX
157.8
Quality ÷ blended $/1M (higher is better)
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Overall (Matrix)
- 31.6
- Cap Intelligence
- 26.1
- AA / Intel index
- 8.8
- Cap Coding
- 36.0
- Matrix Coding
- 45.0
- Input $/1M
- $0.040
- Output $/1M
- $0.16
- Value pts/$
- 130.40
DESCRIPTION + DETAILS
PROVIDER
Sarvam AI
RELEASE
2026-03-06
CONTEXT
131K tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
OPERATOR NOTES
Quality, latency, cost, and failure modes — not marketing copy.
No reviews yet
WRITE A REVIEW
Tap a star to rate
Stored on this device · synced when signed in
No operator notes yet
First review sets the tone for how teams evaluate Sarvam 105B.
MODEL COMPARISON
| Metric |  Sarvam 105B |
|---|---|
| Provider | Sarvam AI |
| Release | 2026-03-06 |
| Input / 1M | $0.04 |
| Output / 1M | $0.16 |
| Context | 131K tokens |
| Cadle Cap | 50 |
| Cap board | Cadle Language Cap 50 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- Supabase models
- Cadle public observations
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
Sarvam AI listing
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Overall31.6
AA IQ8.8
Coding45
Agentic48.1
MMLU93.4
GPQA73.8
Math98.6