Released: 2024-12-03

Amazon Nova Pro 1.0

Highly capable multimodal model combining speed and reasoning across text, documents, images, and video.

Intelligence Index
85.5/ 100
Calibrated multi-domain composite
Throughput Speed
88tok/sec
Output streaming throughput
Time To First Token
310ms
Initial chunk server latency
LiveBench Contam-Free
74.0%
September 2026 suite score

Sourced Benchmark Evaluations (61)

Verified performance across authoritative benchmarks with provenance tracking.
BenchmarkStatusScoreTrustDateSource TypeProvenance
LiveBench (Continuous)Active74%
94
2025-02-01independentSource ↗
ARC-AGI-3Active54.6%
93
2025-01-07independentSource ↗
ARC-AGI-2Nearing Saturation65.5%
75
2024-12-31independentSource ↗
FrontierMathActive23.2%
98
2024-12-28independentSource ↗
PutnamBenchActive43.2%
90
2024-12-27independentSource ↗
Omni-MATHDeprecated61.4%
10
2024-12-25independentSource ↗
SWE-LancerDeprecated51.8%
20
2024-12-25independentSource ↗
SoohakActive63.1%
98
2024-12-23independentSource ↗
FrontierCodeActive44.2%
98
2024-12-23independentSource ↗
Humanity's Last ExamActive37%
93
2024-12-21independentSource ↗
StructFlowBenchNearing Saturation66.9%
75
2024-12-21independentSource ↗
AIMENearing Saturation78.9%
75
2024-12-21independentSource ↗
OlympiadBenchActive68.1%
80
2024-12-20independentSource ↗
FireBenchActive66.1%
95
2024-12-19independentSource ↗
Terminal-BenchActive53.3%
80
2024-12-19independentSource ↗
MathArenaActive66.4%
99
2024-12-19independentSource ↗
OpenAI-MRCRActive71.8%
80
2024-12-18independentSource ↗
CodeContestsDeprecated49.5%
10
2024-12-18independentSource ↗
SimpleQAActive44.5%
90
2024-12-18independentSource ↗
ComplexBenchNearing Saturation64.5%
80
2024-12-17independentSource ↗
SWE-bench ProActive47.2%
90
2024-12-17independentSource ↗
LongBench-ProActive70.1%
80
2024-12-17independentSource ↗
MultiPL-EDeprecated70.1%
10
2024-12-16independentSource ↗
ZeroSCROLLSNearing Saturation68.4%
78
2024-12-16independentSource ↗
AgentIFNearing Saturation53.5%
80
2024-12-15independentSource ↗
MATHSaturated81.3%
25
2024-12-15independentSource ↗
LiveCodeBenchSaturated62.5%
39
2024-12-15independentSource ↗
InfiniteBenchNearing Saturation72.7%
65
2024-12-15independentSource ↗
MMLU-ProNearing Saturation78.7%
75
2024-12-14independentSource ↗
MercuryDeprecated67.1%
10
2024-12-14independentSource ↗
SCROLLSNearing Saturation68.4%
65
2024-12-14independentSource ↗
RULERNearing Saturation78.7%
84
2024-12-13independentSource ↗
TabMWPSaturated76.4%
25
2024-12-13independentSource ↗
CyberSecEvalDeprecated68.6%
10
2024-12-13independentSource ↗
MMLU-ReduxSaturated83.8%
25
2024-12-12independentSource ↗
QuALITYNearing Saturation75.2%
78
2024-12-12independentSource ↗
SWE-bench VerifiedSaturated59.4%
25
2024-12-12independentSource ↗
MGSMNearing Saturation78.9%
65
2024-12-11independentSource ↗
LongBenchNearing Saturation73.5%
65
2024-12-11independentSource ↗
SWE-benchDeprecated51.8%
10
2024-12-11independentSource ↗
AGIEvalSaturated72.2%
25
2024-12-10independentSource ↗
QASPERNearing Saturation71%
65
2024-12-10independentSource ↗
TruthfulQASaturated75.2%
25
2024-12-10independentSource ↗
SuperGLUESaturated85.7%
25
2024-12-09independentSource ↗
GSM-HardDeprecated79.7%
10
2024-12-09independentSource ↗
MT-BenchNearing Saturation8.1%
75
2024-12-08independentSource ↗
BIG-Bench HardSaturated82.3%
25
2024-12-08independentSource ↗
CodeXGLUEDeprecated71.6%
23
2024-12-08independentSource ↗
MBPP+Nearing Saturation77.7%
65
2024-12-07independentSource ↗
WinoGrandeSaturated87.4%
28
2024-12-07independentSource ↗
IFEvalDeprecated77.1%
25
2024-12-07independentSource ↗
GPQANearing Saturation75.2%
78
2024-12-07independentSource ↗
HumanEval+Saturated82.3%
25
2024-12-06independentSource ↗
Needle-in-a-HaystackSaturated97.1%
44
2024-12-06independentSource ↗
CommonsenseQASaturated88.2%
28
2024-12-06independentSource ↗
GSM8KSaturated89.6%
25
2024-12-05independentSource ↗
GLUESaturated90.7%
28
2024-12-05independentSource ↗
MBPPSaturated80.8%
25
2024-12-05independentSource ↗
HumanEvalSaturated86.9%
25
2024-12-04independentSource ↗
MMLUSaturated87.2%
25
2024-12-04independentSource ↗
ARC-AGISaturated79%
25
2024-12-04independentSource ↗
OpenAI Compatible API ExecutionAPI Ready
from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="amazon-nova-pro-v1",
    messages=[{"role": "user", "content": "Evaluate multi-step logic problem"}],
    temperature=0.2
)
print(response.choices[0].message.content)

Evaluation & Sourcing Notes

Scores listed for Amazon Nova Pro 1.0 represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.

All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.